© 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. 34-GEMMASCOPE-RES-131K
    7. 118998
    Prev
    Next
    INDEX
    Explanations

    Board of members

    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_34/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
     halben
    -0.87
     crafty
    -0.84
    ใน
    -0.83
     negocio
    -0.82
     fourrure
    -0.82
     fundamentos
    -0.80
     befinden
    -0.79
     heighten
    -0.78
    ticion
    -0.78
    General
    -0.77
    POSITIVE LOGITS
     of
    2.30
     member
    1.65
     members
    1.52
    members
    1.23
    member
    1.22
     MEMBERS
    1.04
    room
    1.03
    成员
    1.02
     чле
    1.02
    mitglieder
    1.02
    Activations Density 0.010%

    No Known Activations