© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104
    Prev
    Next
    INDEX
    Explanations

    policing, Steelers, SQLite

    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
    椟
    -2.50
    縂
    -2.44
    ciam
    -2.42
    蹋
    -2.42
    CHREIB
    -2.38
    iato
    -2.34
    âteau
    -2.28
    lifford
    -2.27
    弉
    -2.20
    iorno
    -2.19
    POSITIVE LOGITS
    u
    3.91
     für
    3.33
     برای
    3.22
    S
    3.20
    ll
    3.00
    }$
    3.00
    r
    2.80
     untuk
    2.75
    a
    2.73
    re
    2.72
    Activations Density 0.007%

    No Known Activations