© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44082
    Prev
    Next
    INDEX
    Explanations

    folding actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ς
    2.36
    ש
    2.22
    蠻
    1.83
     ★★
    1.80
    此同时
    1.79
    <0x83>
    1.73
    five
    1.73
    Три
    1.70
    ش
    1.69
     PartialEq
    1.68
    POSITIVE LOGITS
     defaultstate
    2.23
    اد
    2.11
    ू
    2.11
    ierten
    2.02
    았
    2.02
     direto
    1.93
     große
    1.91
    ية
    1.88
     Надо
    1.88
    ющий
    1.87
    Activations Density 0.004%

    No Known Activations