© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93231
    Prev
    Next
    INDEX
    Explanations

    dimensionless and normalized quantities

    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_22/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
    Not
    -0.91
    ѵ
    -0.87
    Some
    -0.86
     out
    -0.85
    tafogo
    -0.82
    Tinh
    -0.82
    Most
    -0.79
    eded
    -0.77
     cabin
    -0.76
    Havolalar
    -0.76
    POSITIVE LOGITS
    metazone
    0.89
     dimensionless
    0.85
     import
    0.84
    ButtonGroup
    0.82
    zeits
    0.81
    yyb
    0.81
     FontFamily
    0.80
    ᴢ
    0.80
     Prüfung
    0.78
    anthemum
    0.77
    Activations Density 0.023%

    No Known Activations