© 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. 123712
    Prev
    Next
    INDEX
    Explanations

    There are

    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
     of
    -2.61
     believes
    -2.28
     at
    -2.28
     because
    -2.16
     provides
    -2.13
     Since
    -2.13
     when
    -2.03
     during
    -1.96
    </h3>
    -1.95
     if
    -1.93
    POSITIVE LOGITS
    ౧
    2.70
     verschillende
    2.53
    
    2.27
    ౬
    2.25
    ﮟ
    2.23
    actéristi
    2.20
     REALLY
    2.19
    ਃ
    2.17
    撂
    2.17
    without
    2.17
    Activations Density 0.003%

    No Known Activations