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. 8690
    Prev
    Next
    INDEX
    Explanations

    place names and French regions

    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
     commissioners
    -0.76
    clays
    -0.75
     longe
    -0.73
    Proceso
    -0.69
    ='"
    -0.69
     Pender
    -0.69
    ombs
    -0.68
     sanctions
    -0.68
    setClass
    -0.67
    ̌
    -0.67
    POSITIVE LOGITS
     Strasbourg
    0.91
     Racine
    0.88
     Basel
    0.85
    Basel
    0.84
    Alsace
    0.82
    nomin
    0.78
     Woodstock
    0.78
     gedeelte
    0.74
    arai
    0.73
    Lach
    0.73
    Activations Density 0.034%

    No Known Activations