© 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. 31699
    Prev
    Next
    INDEX
    Explanations

    Vanderbilt University

    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
    dańsk
    -0.70
     Challenger
    -0.70
    くなり
    -0.70
     fo
    -0.69
     Toh
    -0.69
    ALF
    -0.68
     Pats
    -0.66
    colle
    -0.65
     SRT
    -0.65
     saltar
    -0.65
    POSITIVE LOGITS
     Vanderbilt
    1.63
    Vander
    1.09
     VU
    1.06
    VU
    0.98
     Nashville
    0.90
    ThemeProvider
    0.88
    bilt
    0.86
    dhist
    0.82
     التواصل
    0.78
    デニム
    0.75
    Activations Density 0.025%

    No Known Activations