Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7802
    Prev
    Next
    INDEX
    Explanations

    code comments and copyright notices

    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
     inté
    -0.74
     Text
    -0.71
     enrich
    -0.69
    ataires
    -0.67
     Powell
    -0.67
    update
    -0.66
    know
    -0.66
     Know
    -0.66
     Г
    -0.65
     Tu
    -0.65
    POSITIVE LOGITS
    ፕ
    0.79
    Irlande
    0.73
     interment
    0.72
    resourceId
    0.71
     Huerta
    0.70
     disques
    0.68
     Footprint
    0.68
     matéria
    0.68
    レン
    0.67
     Claimant
    0.67
    Activations Density 0.045%

    No Known Activations