© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2944
    Prev
    Next
    INDEX
    Explanations

    Year, length, or Day

    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
    ter
    0.92
    is
    0.86
    lari
    0.83
    f
    0.81
    ol
    0.79
     dotyczą
    0.77
    ac
    0.73
    le
    0.71
    zare
    0.71
    j
    0.71
    POSITIVE LOGITS
    のス
    0.72
     время
    0.70
    ﾗ
    0.67
     phasor
    0.65
    الس
    0.64
     xgboost
    0.64
     edad
    0.63
     emeritus
    0.63
    ﺮ
    0.63
    ኀ
    0.63
    Activations Density 0.693%

    No Known Activations