© 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. 107883
    Prev
    Next
    INDEX
    Explanations

    coefficient of

    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
    Ceramic
    -0.79
     sonrisa
    -0.79
    Broker
    -0.77
     convene
    -0.76
     ewig
    -0.75
     mentira
    -0.74
    frozen
    -0.73
     庭
    -0.73
    Berger
    -0.72
    Ciudad
    -0.71
    POSITIVE LOGITS
     coefficient
    2.00
     Coefficient
    1.91
    coefficient
    1.73
    Coefficient
    1.58
     coeff
    1.56
     coef
    1.54
    coeff
    1.43
     Coefficients
    1.42
    Coeff
    1.35
     coefficients
    1.34
    Activations Density 0.013%

    No Known Activations