© 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. 41394
    Prev
    Next
    INDEX
    Explanations

    compact, traditional, robot

    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
     smeared
    0.81
     neglig
    0.77
    োপুরি
    0.76
    翕
    0.75
     fitted
    0.73
     actuated
    0.73
     equips
    0.73
    an
    0.71
     saves
    0.71
    "<<
    0.71
    POSITIVE LOGITS
    Kom
    0.96
    З
    0.86
    nombre
    0.86
    Κ
    0.84
     З
    0.81
    UEFA
    0.80
     postseason
    0.80
     Конститу
    0.80
     Thông
    0.78
    Хо
    0.77
    Activations Density 0.000%

    No Known Activations