© 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. 57075
    Prev
    Next
    INDEX
    Explanations

    measurements and indicators

    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
    IsOptional
    -0.82
    ﻠ
    -0.79
    amenta
    -0.79
    ücke
    -0.79
    ầm
    -0.77
     烤
    -0.77
    centages
    -0.75
     없
    -0.73
    ża
    -0.73
    ủy
    -0.73
    POSITIVE LOGITS
     measure
    4.53
     measures
    4.16
    measure
    3.39
    Measure
    3.19
     Measures
    3.14
    Measures
    3.14
    measures
    3.09
     Measure
    2.88
     indicators
    2.64
     indicator
    2.63
    Activations Density 0.238%

    No Known Activations