© 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. 22-GEMMASCOPE-RES-131K
    7. 84104
    Prev
    Next
    INDEX
    Explanations

    speaker attribution names

    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_22/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
     is
    -1.13
     einigen
    -1.12
    笑笑
    -1.11
     algunos
    -1.09
     beberapa
    -1.04
    頷
    -1.03
     otros
    -1.02
     aquellos
    -1.01
    ulents
    -1.01
     You
    -1.00
    POSITIVE LOGITS
     auffi
    1.13
     budapest
    1.13
     boute
    1.13
     prenn
    1.07
     helg
    1.05
     smör
    1.05
    鲧
    1.03
    鮡
    1.01
    說
    1.01
     andré
    1.01
    Activations Density 0.012%

    No Known Activations