© 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. 112260
    Prev
    Next
    INDEX
    Explanations

    titles or headings

    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
     interesado
    -1.83
     fondament
    -1.76
     България
    -1.65
    拳头
    -1.65
    篓
    -1.63
     dispuestos
    -1.62
    -¡
    -1.62
     temprano
    -1.60
     парке
    -1.59
     mineures
    -1.59
    POSITIVE LOGITS
    .
    1.41
     кусо
    1.40
     didn
    1.30
     lusso
    1.28
    ).
    1.23
     not
    1.23
     plenty
    1.20
    我在
    1.20
    vaila
    1.19
    …
    1.19
    Activations Density 0.009%

    No Known Activations