© 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. 67358
    Prev
    Next
    INDEX
    Explanations

    image credit or caption

    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
     three
    -2.14
     nine
    -2.02
     in
    -1.95
     eight
    -1.90
     five
    -1.88
     this
    -1.82
    vosť
    -1.79
     four
    -1.70
     because
    -1.70
     longstanding
    -1.67
    POSITIVE LOGITS
     одного
    1.90
    栳
    1.76
     ۱۵
    1.73
    敺
    1.64
     But
    1.64
     ‚
    1.63
     perro
    1.62
    鲠
    1.62
    臵
    1.60
     iſt
    1.59
    Activations Density 0.007%

    No Known Activations