© 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. 110576
    Prev
    Next
    INDEX
    Explanations

    card deck

    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
    ienza
    -0.76
     monnaie
    -0.75
    splitContainer
    -0.72
    Capsule
    -0.71
     Marsden
    -0.70
    윅
    -0.69
    insel
    -0.69
     Kugel
    -0.69
     democracies
    -0.68
    citizens
    -0.67
    POSITIVE LOGITS
     deck
    3.22
    deck
    2.70
     Deck
    2.69
     decks
    2.66
    Deck
    2.55
     DECK
    2.19
     Decks
    2.16
    decks
    1.95
     cards
    1.81
     tarot
    1.63
    Activations Density 0.026%

    No Known Activations