© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9008
    Prev
    Next
    INDEX
    Explanations

    only remaining

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is spotting words that convey exclusivity or uniqueness (e.g. “only,” “sole,” “last”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases emphasizing exclusivity or limitation, particularly "the only" followed by a noun.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    constructions that emphasize exclusivity or singularity, framing something as the sole, single, or last option/instance remaining.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    many
    0.77
    smaller
    0.75
    ibility
    0.68
     muitos
    0.66
    いろんな
    0.65
    ز
    0.65
    غ
    0.65
    ם
    0.64
     many
    0.64
    ต่างๆ
    0.64
    POSITIVE LOGITS
     एकमात्र
    1.41
     অবশিষ্ট
    1.20
     einzigen
    1.18
     лишь
    1.17
     Remaining
    1.15
     remaining
    1.14
     eneste
    1.13
     einzige
    1.09
    しか
    1.08
     একমাত্র
    1.05
    Activations Density 0.481%

    No Known Activations