© 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. 22-GEMMASCOPE-RES-131K
    7. 26492
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     like
    -1.08
     itself
    -0.92
     know
    -0.91
    》：
    -0.85
     Συ
    -0.85
    遵循
    -0.84
    )}</
    -0.83
    Giá
    -0.80
    FFEE
    -0.80
    })));
    -0.78
    POSITIVE LOGITS
     equipments
    0.95
    ukary
    0.95
     kajian
    0.94
    -_
    0.92
     seperate
    0.91
    地说道
    0.87
     puissent
    0.87
    -^
    0.85
     tante
    0.85
     Lando
    0.85
    Activations Density 0.003%

    No Known Activations