© 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. 110543
    Prev
    Next
    INDEX
    Explanations

    Camden locations and organizations

    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
     resear
    -0.78
     mower
    -0.76
     Pascual
    -0.72
    Costo
    -0.72
    ᆺ
    -0.71
     barra
    -0.70
    TEMPO
    -0.68
    咻
    -0.68
    MTA
    -0.68
     tans
    -0.67
    POSITIVE LOGITS
     демо
    0.70
    üst
    0.70
     Newtonsoft
    0.69
    addMessage
    0.67
     встречи
    0.66
     Avalon
    0.66
     sendMessage
    0.66
     activates
    0.66
    Bij
    0.64
     activating
    0.64
    Activations Density 0.069%

    No Known Activations