© 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. 118942
    Prev
    Next
    INDEX
    Explanations

    turn followed by key, on, or pike

    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
    0
    -0.93
    훙
    -0.88
     Nh
    -0.88
     klarer
    -0.88
    lijke
    -0.84
     loamy
    -0.81
     contradicted
    -0.81
     vierte
    -0.80
    vett
    -0.80
    г
    -0.80
    POSITIVE LOGITS
     Turn
    1.15
    pike
    1.10
    buckle
    0.98
    coat
    0.96
    beutel
    0.95
    arounds
    0.94
    Turn
    0.94
     nią
    0.94
    Zep
    0.92
    Rhône
    0.90
    Activations Density 0.018%

    No Known Activations