© 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. 20087
    Prev
    Next
    INDEX
    Explanations

    around the number 40

    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
     Hinblick
    -3.09
    樒
    -2.77
    
    -2.63
     verbess
    -2.48
     fueran
    -2.45
    ktm
    -2.39
    
    -2.38
     escond
    -2.38
     zbo
    -2.34
     pokoj
    -2.33
    POSITIVE LOGITS
    nt
    2.97
    m
    2.78
    mu
    2.52
    f
    2.47
    ar
    2.41
    r
    2.30
     lakini
    2.25
     es
    2.23
    fi
    2.23
    u
    2.20
    Activations Density 0.034%

    No Known Activations