© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13670
    Prev
    Next
    INDEX
    Explanations

    why why why

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

    The neuron fires on low‐frequency or unusual tokens (e.g. uncommon words, numbers, punctuation like ellipses, the pronoun “I,” etc.).

    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
     fashioned
    0.70
    ''_
    0.69
    HIV
    0.68
     intégral
    0.68
    ान्य
    0.66
     grot
    0.66
    eous
    0.65
    o
    0.65
    unlink
    0.64
    uring
    0.64
    POSITIVE LOGITS
    бах
    0.78
    жела
    0.77
    תה
    0.75
     empecé
    0.75
    ເຂ
    0.74
    се
    0.73
    ع
    0.70
    מש
    0.70
    ৯৫
    0.70
    슨
    0.70
    Activations Density 0.001%

    No Known Activations