© 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. 103059
    Prev
    Next
    INDEX
    Explanations

    row with attributes or layout

    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
    ing
    -2.72
    觏
    -2.61
    .
    -2.55
    U
    -2.55
    F
    -2.50
     There
    -2.44
    ”
    -2.38
    a
    -2.36
    荩
    -2.36
    ;
    -2.30
    POSITIVE LOGITS
    翃
    2.86
     enchanting
    2.81
    ............
    2.73
     göm
    2.64
    !"
    2.63
    鶿
    2.59
    ⸂
    2.58
    ..........
    2.58
    .............
    2.52
    鏐
    2.50
    Activations Density 0.004%

    No Known Activations