© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 524
    Prev
    Next
    INDEX
    Explanations

    websocket connections

    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
     oppure
    -1.75
     gangen
    -1.72
     hvil
    -1.63
     staffel
    -1.58
     balans
    -1.58
    洐
    -1.56
    杁
    -1.54
    遄
    -1.54
     sekunder
    -1.54
    quelize
    -1.54
    POSITIVE LOGITS
    \
    2.03
     двумя
    1.77
    uruhan
    1.76
    viembre
    1.60
     Что
    1.51
    neling
    1.51
    poons
    1.50
    仮面
    1.48
    ürnberg
    1.48
    änemark
    1.43
    Activations Density 0.010%

    No Known Activations