© 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. 110460
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and physics terms

    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
    Gamb
    -0.76
    inazione
    -0.75
    mazda
    -0.68
     Scheiben
    -0.67
     constrained
    -0.67
    SessionId
    -0.66
    脱
    -0.66
     Ames
    -0.66
    Twisted
    -0.66
    ং
    -0.65
    POSITIVE LOGITS
     cutoff
    0.87
     pairwise
    0.87
     LJ
    0.83
     neighbor
    0.81
     décrit
    0.81
     lubric
    0.80
     venda
    0.80
     Maarten
    0.79
     tabled
    0.78
     gole
    0.78
    Activations Density 0.008%

    No Known Activations