© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123717
    Prev
    Next
    INDEX
    Explanations

    people in relation to others

    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
     even
    -1.56
     also
    -1.55
     of
    -1.48
     zarówno
    -1.45
     nawet
    -1.39
     well
    -1.35
     what
    -1.35
     meeting
    -1.33
     you
    -1.32
     także
    -1.29
    POSITIVE LOGITS
     betek
    1.48
    -<
    1.31
     verhe
    1.27
    
    1.27
    álás
    1.25
     eene
    1.20
    Keine
    1.16
     kunna
    1.15
    லா
    1.15
    Они
    1.14
    Activations Density 0.039%

    No Known Activations