© 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. 1909
    Prev
    Next
    INDEX
    Explanations

    reward for information

    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
    饜
    -1.77
    '
    -1.70
    naments
    -1.61
    鲧
    -1.60
     sali
    -1.55
     XXXI
    -1.55
     bronz
    -1.52
     murale
    -1.51
     XXIX
    -1.50
     maro
    -1.50
    POSITIVE LOGITS
     \
    2.03
    тинга
    1.62
    </em>
    1.52
     nachfol
    1.44
     cuya
    1.38
     derzeit
    1.37
     polling
    1.30
    就此
    1.30
     refiri
    1.30
    ที่
    1.30
    Activations Density 0.016%

    No Known Activations