© 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. 57645
    Prev
    Next
    INDEX
    Explanations

    finding view by id

    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
     and
    -1.92
    ↵↵↵
    -1.77
    }$
    -1.66
    ，”
    -1.62
    ig
    -1.56
    6
    -1.56
    You
    -1.55
    记得
    -1.55
    ris
    -1.53
    es
    -1.52
    POSITIVE LOGITS
    夲
    2.09
    峮
    1.95
     apporte
    1.90
     of
    1.88
    coledì
    1.86
    槼
    1.81
     logros
    1.69
     anbef
    1.64
     itinéraires
    1.64
    髕
    1.63
    Activations Density 0.011%

    No Known Activations