© 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. 41943
    Prev
    Next
    INDEX
    Explanations

    ' form:' followed by syntax

    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
     rebels
    0.82
     Ease
    0.80
     ease
    0.79
     narciss
    0.76
    rug
    0.76
    rails
    0.74
     e
    0.73
    az
    0.73
     번
    0.73
    jo
    0.73
    POSITIVE LOGITS
    络
    0.90
     Wasn
    0.84
    一副
    0.82
    oq
    0.79
    dard
    0.77
    gawa
    0.77
     sottop
    0.77
    行列
    0.76
     obligé
    0.76
    aş
    0.76
    Activations Density 0.000%

    No Known Activations