© 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. 129962
    Prev
    Next
    INDEX
    Explanations

    read our

    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
     When
    -1.64
     It
    -1.49
    r
    -1.45
    s
    -1.45
     There
    -1.45
    )
    -1.42
    ),
    -1.42
     Neither
    -1.36
     Many
    -1.35
     Knowing
    -1.33
    POSITIVE LOGITS
     kapture
    1.65
     hunne
    1.64
    卌
    1.57
     groote
    1.52
     ￥
    1.49
    蠖
    1.48
    ₶
    1.48
    蚰
    1.45
     zeven
    1.42
     incrí
    1.41
    Activations Density 0.056%

    No Known Activations