© 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. 86209
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames or descriptors

    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
    y
    -3.98
     With
    -3.14
    X
    -3.11
    With
    -2.95
    In
    -2.77
    O
    -2.64
    in
    -2.63
    Other
    -2.61
    si
    -2.52
    d
    -2.52
    POSITIVE LOGITS
    髫
    3.06
    驀
    2.78
    踽
    2.70
    蒌
    2.50
    bility
    2.45
    嘰
    2.44
    ität
    2.41
     \%
    2.39
    蛩
    2.36
     və
    2.31
    Activations Density 0.003%

    No Known Activations