© 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. 118861
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

    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
    sib
    -0.75
    TableColumn
    -0.75
    🛶
    -0.73
     endroit
    -0.73
    getNode
    -0.72
     Tid
    -0.71
     "").
    -0.70
     energ
    -0.70
    iconSize
    -0.69
    afford
    -0.68
    POSITIVE LOGITS
     proč
    0.77
     (__
    0.73
     potrzebu
    0.71
    entraî
    0.71
     využ
    0.70
     unabhäng
    0.69
     risult
    0.66
    さっき
    0.66
     करेंगे
    0.66
    horario
    0.65
    Activations Density 0.068%

    No Known Activations