© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5357
    Prev
    Next
    INDEX
    Explanations

    introduced directly

    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_24_width_16k_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
    na
    0.96
    NA
    0.87
    ק
    0.87
    на
    0.83
    те
    0.77
    st
    0.77
    ס
    0.76
    ور
    0.73
    ח
    0.73
    te
    0.72
    POSITIVE LOGITS
     éclair
    0.86
     undivided
    0.84
     guér
    0.80
     extrême
    0.80
     feu
    0.79
     individus
    0.79
     けれど
    0.77
     anticoagulant
    0.75
     unrelated
    0.75
    olactone
    0.75
    Activations Density 0.001%

    No Known Activations