© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108709
    Prev
    Next
    INDEX
    Explanations

    code structure classification

    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
     carelessness
    -0.69
     Bere
    -0.68
    bertas
    -0.67
     PU
    -0.67
     sausage
    -0.67
     Bet
    -0.66
     Kaffee
    -0.66
     Cop
    -0.65
     Att
    -0.64
    Synopsis
    -0.64
    POSITIVE LOGITS
    bugging
    0.78
     Outputs
    0.72
    Vegeta
    0.70
    dragons
    0.67
     Crescent
    0.67
     chyba
    0.66
     inquest
    0.66
     entendu
    0.65
     официаль
    0.65
     hogar
    0.65
    Activations Density 0.070%

    No Known Activations