© 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. 118740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    上了
    -0.82
    ఓ
    -0.82
     servant
    -0.81
     rebate
    -0.81
     링크
    -0.80
     subspecies
    -0.80
     registration
    -0.80
     reservation
    -0.79
     Asthma
    -0.79
    ellemző
    -0.77
    POSITIVE LOGITS
     Datenschutzer
    0.78
    助
    0.71
    宰
    0.68
     associated
    0.67
     Sicht
    0.66
    lcl
    0.66
     Pira
    0.65
     Integer
    0.65
    dras
    0.65
    ás
    0.65
    Activations Density 0.000%

    No Known Activations