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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6949
    Prev
    Next
    INDEX
    Explanations

    minimizing restraints

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

    The neuron spikes strongly on low‐frequency, multi‐syllabic “content” tokens (i.e. uncommon words).

    oai_token-act-pair · o4-miniTriggered 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
     تیم
    0.85
     különböző
    0.84
     طراحی
    0.78
     डिप्टी
    0.78
    ƅ
    0.78
     টেলিভিশন
    0.77
    ל
    0.77
     های
    0.77
    コレート
    0.76
    틸
    0.75
    POSITIVE LOGITS
    nets
    0.87
    nél
    0.83
    nent
    0.82
    ,...,
    0.77
    nA
    0.76
    cation
    0.75
    nT
    0.75
    nq
    0.75
    nThe
    0.75
    nid
    0.74
    Activations Density 0.000%

    No Known Activations