© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162400
    Prev
    Next
    INDEX
    Explanations

    Pandora bridge

    np_acts-logits-general · gemini-2.5-flash-lite

    advice and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    م
    0.57
    \
    0.52
    %",
    0.48
    ,"
    0.47
     depressing
    0.47
    로는
    0.46
    ए
    0.46
     ",
    0.45
     \
    0.45
    い
    0.45
    POSITIVE LOGITS
    positroid
    0.52
    शिला
    0.52
    URANCE
    0.50
    ancellationToken
    0.48
    apayati
    0.48
     വിൽപ്പന
    0.48
     défis
    0.47
     Ironman
    0.47
    綢
    0.47
     Bretagne
    0.47
    Activations Density 0.000%

    No Known Activations