© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36064
    Prev
    Next
    INDEX
    Explanations

    to define

    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
    IR
    0.77
    illent
    0.77
    illin
    0.74
    ik
    0.73
    IME
    0.73
    istin
    0.70
    гина
    0.70
    ط
    0.70
    ме
    0.70
    iores
    0.69
    POSITIVE LOGITS
     الاعدادي
    0.88
     talaga
    0.84
    ៤
    0.83
     thưởng
    0.77
     tóc
    0.77
    ᱑
    0.77
     Ache
    0.76
    弯
    0.75
    "]))
    0.75
    >:</
    0.74
    Activations Density 0.000%

    No Known Activations