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. 8743
    Prev
    Next
    INDEX
    Explanations

    CI CD pipelines and scheduled tasks

    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
     Inoc
    -0.81
    FlatButton
    -0.71
    ecma
    -0.69
     inoc
    -0.67
     الأص
    -0.67
     Boeh
    -0.66
    Lager
    -0.66
     Technologie
    -0.62
    通知
    -0.62
     Nathalie
    -0.61
    POSITIVE LOGITS
     pipeline
    2.98
     pipelines
    2.81
    pipeline
    2.42
     Pipeline
    2.31
    Pipeline
    2.30
     Pip
    1.88
    Pip
    1.86
    パイプ
    1.58
    pip
    1.58
     pip
    1.50
    Activations Density 0.076%

    No Known Activations