© 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. 78954
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations

    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
     packed
    -0.82
     criado
    -0.74
    meaux
    -0.73
     thành
    -0.71
    ვ
    -0.70
    '`
    -0.70
    就職
    -0.70
    éos
    -0.69
     Opp
    -0.68
    ENING
    -0.68
    POSITIVE LOGITS
     math
    0.89
    肆
    0.86
     maths
    0.86
    sividad
    0.85
    MathML
    0.85
    nativeElement
    0.84
    math
    0.83
    Calculus
    0.82
     spline
    0.79
    Math
    0.79
    Activations Density 0.001%

    No Known Activations