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. 8393
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
     delusions
    -0.80
    MMV
    -0.75
    ncia
    -0.74
    に見える
    -0.73
    <b>
    -0.73
     poste
    -0.72
    oob
    -0.71
    ुर
    -0.71
    printk
    -0.70
    闇
    -0.70
    POSITIVE LOGITS
     indicar
    0.87
     there
    0.79
    hdysval
    0.79
     article
    0.79
    artament
    0.78
     popping
    0.78
     faster
    0.78
     sidste
    0.77
     bitte
    0.77
     month
    0.77
    Activations Density 0.009%

    No Known Activations