© 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. 107212
    Prev
    Next
    INDEX
    Explanations

    checks made payable to

    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
     Susquehanna
    -0.70
     Covered
    -0.69
    VII
    -0.68
     voix
    -0.68
     viajes
    -0.67
    dibu
    -0.64
    rises
    -0.63
    ης
    -0.63
    venty
    -0.63
     prix
    -0.63
    POSITIVE LOGITS
     benef
    0.69
    }}^
    0.65
     Artik
    0.65
    戛
    0.65
    Interv
    0.64
    rich
    0.64
    vano
    0.63
     Matos
    0.63
     vidi
    0.63
    鬱
    0.63
    Activations Density 0.054%

    No Known Activations