Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8682
    Prev
    Next
    INDEX
    Explanations

    client ID and secrets

    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
     Spinning
    -0.65
     trusts
    -0.65
     hummus
    -0.64
     ardour
    -0.64
     살
    -0.62
     Nave
    -0.61
     Sina
    -0.61
    行的
    -0.61
    March
    -0.60
    afar
    -0.60
    POSITIVE LOGITS
    bjerg
    0.73
     National
    0.70
     ticket
    0.67
    轰
    0.66
    kách
    0.66
    createComponent
    0.65
    gered
    0.65
    dicion
    0.64
    Polen
    0.64
    Supervisor
    0.64
    Activations Density 0.044%

    No Known Activations