© 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. 118842
    Prev
    Next
    INDEX
    Explanations

    electrical supply voltages

    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
     kesadaran
    -0.68
    들은
    -0.65
    rotta
    -0.65
    饌
    -0.65
     Griffith
    -0.65
    部隊
    -0.64
    硏
    -0.64
     Monica
    -0.64
    reservation
    -0.63
     Julie
    -0.63
    POSITIVE LOGITS
     supply
    1.80
     Supply
    1.42
    Supply
    1.38
     SUPPLY
    1.34
     supplies
    1.27
    SUPPLY
    1.20
    supply
    1.19
     Supplies
    1.03
    SUP
    0.96
    versorgung
    0.95
    Activations Density 0.023%

    No Known Activations