© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74173
    Prev
    Next
    INDEX
    Explanations

    places and regions

    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_10/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
     princesas
    -1.58
    Neden
    -1.55
    垕
    -1.52
     our
    -1.49
    vielen
    -1.49
    𖥦
    -1.48
     Например
    -1.48
    Yeet
    -1.44
    Vaya
    -1.41
     hanno
    -1.39
    POSITIVE LOGITS
    %);
    1.38
    ebly
    1.35
    ↵
    1.35
    osaurus
    1.35
    
    1.30
    ",
    1.30
    oes
    1.25
    
    1.22
    逦
    1.22
    ま
    1.22
    Activations Density 0.113%

    No Known Activations