© 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. 59985
    Prev
    Next
    INDEX
    Explanations

    names after certain endings

    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
     sicheren
    -2.38
     ewigen
    -2.30
     größten
    -2.23
     individuellen
    -2.08
     besonderen
    -2.06
     schnellen
    -2.02
     täglichen
    -1.97
     einzigartigen
    -1.92
     himself
    -1.91
     gewährleisten
    -1.88
    POSITIVE LOGITS
     herself
    2.61
     positivas
    1.83
    e
    1.75
     obtenidos
    1.68
    mme
    1.64
     która
    1.63
    esh
    1.60
    苼
    1.57
     childish
    1.56
     yako
    1.56
    Activations Density 0.521%

    No Known Activations