© 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. 118655
    Prev
    Next
    INDEX
    Explanations

    Remote communication

    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
     Efficiency
    -0.73
    px
    -0.71
     connectivity
    -0.71
    🍳
    -0.71
    namen
    -0.71
    ቋ
    -0.70
     convert
    -0.70
    pl
    -0.69
    </blockquote>
    -0.69
    ogen
    -0.69
    POSITIVE LOGITS
     lidar
    0.89
     Nac
    0.84
     yaw
    0.83
    Nac
    0.81
    äjä
    0.80
     yield
    0.79
    IEC
    0.77
     נע
    0.77
     ბ
    0.76
    arrings
    0.75
    Activations Density 0.015%

    No Known Activations