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. 287
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    第一章
    -0.96
     reportedly
    -0.86
     кризи
    -0.83
    __(/*!
    -0.83
    towns
    -0.81
    endedor
    -0.81
    قيقي
    -0.81
     departament
    -0.81
    rounder
    -0.80
    isNotEmpty
    -0.79
    POSITIVE LOGITS
     eighth
    1.26
     ninth
    1.19
     fifth
    1.16
     seventh
    1.13
     sixth
    1.10
    第
    1.10
     dalších
    0.99
     pagare
    0.97
     zimní
    0.95
     oś
    0.94
    Activations Density 0.046%

    No Known Activations