© 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. 92843
    Prev
    Next
    INDEX
    Explanations

    public in programming 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
    defineProperty
    -0.91
     final
    -0.89
    final
    -0.83
    scm
    -0.79
    最終
    -0.77
     finalmente
    -0.76
    vana
    -0.75
     advierte
    -0.75
     سوريا
    -0.73
     canh
    -0.73
    POSITIVE LOGITS
    nosť
    0.93
     externi
    0.93
     void
    0.92
    chemy
    0.88
     parallax
    0.86
     Portail
    0.84
     zich
    0.83
    izarse
    0.82
     fresco
    0.81
    bieg
    0.79
    Activations Density 0.003%

    No Known Activations