© 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. 109741
    Prev
    Next
    INDEX
    Explanations

    github.com/grpc/codes/<!DOCTYPE

    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
    autique
    -0.77
    лить
    -0.73
     Bahrain
    -0.72
     Hick
    -0.69
     convulsions
    -0.68
    HW
    -0.68
     Exams
    -0.67
     granola
    -0.67
     Tierra
    -0.66
    érale
    -0.66
    POSITIVE LOGITS
    gpr
    0.94
    GPR
    0.86
    valg
    0.79
     απο
    0.79
    cinating
    0.77
     channel
    0.77
    ubei
    0.77
     GPR
    0.77
    grpc
    0.76
     hè
    0.75
    Activations Density 0.025%

    No Known Activations