© 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. 100683
    Prev
    Next
    INDEX
    Explanations

    fractions of an inch

    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
    0
    -2.97
    ーめん
    -2.64
     infamous
    -2.59
    ୪
    -2.44
    食感
    -2.31
     ด้วย
    -2.28
    ꔛ
    -2.28
    providedIn
    -2.28
    gucigalpa
    -2.25
     adorable
    -2.22
    POSITIVE LOGITS
    ization
    2.75
    '
    2.64
     of
    2.48
    acterísticas
    2.41
     Parlamento
    2.31
     \&
    2.25
    栊
    2.23
    釹
    2.23
    埽
    2.22
     bénévol
    2.20
    Activations Density 0.001%

    No Known Activations