© 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. 77698
    Prev
    Next
    INDEX
    Explanations

    Google APIs and code

    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
    atív
    -0.86
     Luxor
    -0.86
    ンク
    -0.83
     VHF
    -0.82
     Bursa
    -0.82
     nitro
    -0.81
     Superhero
    -0.81
    rativa
    -0.80
     '?'
    -0.79
     Dany
    -0.78
    POSITIVE LOGITS
    bowler
    0.77
     Але
    0.73
     "[
    0.72
     commonly
    0.72
     адап
    0.69
     Kräuter
    0.69
    voegen
    0.69
    LikeLike
    0.69
     культура
    0.68
     карт
    0.67
    Activations Density 0.022%

    No Known Activations