© 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. 109685
    Prev
    Next
    INDEX
    Explanations

    head

    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
     покри
    -0.87
    SECTOR
    -0.84
     kitab
    -0.77
     grating
    -0.77
     দেখ
    -0.76
    amore
    -0.76
     muối
    -0.74
    itania
    -0.73
    arm
    -0.73
    νομ
    -0.73
    POSITIVE LOGITS
     head
    1.18
     Head
    1.09
    Head
    1.09
    head
    0.99
     HEAD
    0.98
     decap
    0.83
    HEAD
    0.82
     felt
    0.76
    sé
    0.75
     круп
    0.73
    Activations Density 0.042%

    No Known Activations