© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82223
    Prev
    Next
    INDEX
    Explanations

    consequences and legacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ロール
    0.50
    D
    0.50
    お金
    0.48
    저
    0.47
    Д
    0.46
    낯
    0.46
     firearms
    0.45
    あり
    0.45
    달
    0.45
    J
    0.44
    POSITIVE LOGITS
    etragen
    0.59
     المنتج
    0.55
     cảm
    0.55
     produse
    0.54
    \,.
    0.52
    igste
    0.52
    芢
    0.51
     இணைந்து
    0.51
     مما
    0.50
    ensuche
    0.50
    Activations Density 0.001%

    No Known Activations