© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117758
    Prev
    Next
    INDEX
    Explanations

    socket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungeons
    -0.90
     ancho
    -0.88
    ことで
    -0.86
    cryption
    -0.82
    ,-
    -0.81
    فرم
    -0.81
     Neben
    -0.80
    遅
    -0.80
    oley
    -0.79
    SearchResult
    -0.77
    POSITIVE LOGITS
     wrench
    1.02
    ochim
    0.85
    iries
    0.85
    orsa
    0.83
    uerto
    0.83
     mesto
    0.82
    دد
    0.81
     MISCELLANEOUS
    0.81
     Uncategorized
    0.81
    tagPool
    0.80
    Activations Density 0.018%

    No Known Activations