© 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. 10-GEMMASCOPE-RES-131K
    7. 128937
    Prev
    Next
    INDEX
    Explanations

    bit and bite variations

    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
    ’
    -2.05
    m
    -2.02
    ’，
    -1.90
     there
    -1.86
    I
    -1.83
    ша
    -1.77
    >
    -1.75
    焢
    -1.72
    عتبر
    -1.72
    袮
    -1.69
    POSITIVE LOGITS
    ౭
    2.55
    </i>
    2.20
    鸸
    2.16
     afectado
    1.91
    
    1.86
    笵
    1.82
    ︲
    1.82
     momentous
    1.81
     unſ
    1.81
     vijf
    1.80
    Activations Density 0.009%

    No Known Activations