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. 7685
    Prev
    Next
    INDEX
    Explanations

    trails and routes

    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
    ミナ
    -0.85
    驾驶
    -0.78
    cedentes
    -0.74
    Verlag
    -0.73
    yka
    -0.73
    wijs
    -0.71
    factura
    -0.71
    iencias
    -0.71
    lamine
    -0.71
    orations
    -0.71
    POSITIVE LOGITS
     trail
    2.09
     bike
    1.91
     trails
    1.90
     path
    1.56
    bike
    1.48
     paths
    1.47
     cycle
    1.46
     bicycle
    1.41
     pathway
    1.32
    path
    1.30
    Activations Density 0.027%

    No Known Activations