© 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. 72274
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     copos
    -1.15
    IOT
    -1.14
    
    -1.08
    drawSprites
    -1.07
     après
    -1.06
    过度
    -1.05
    ≔
    -1.05
    щаются
    -1.02
    manya
    -1.02
     produkter
    -1.02
    POSITIVE LOGITS
     one
    1.24
     yourself
    1.20
     becomes
    1.13
     because
    1.13
     from
    1.13
     with
    1.06
     Although
    1.00
     extraordinarily
    1.00
     Once
    1.00
     makes
    0.98
    Activations Density 0.001%

    No Known Activations