© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118999
    Prev
    Next
    INDEX
    Explanations

    dates and court decisions

    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
    Consumed
    -0.73
    အ
    -0.71
     past
    -0.70
     in
    -0.69
     cant
    -0.69
     came
    -0.67
     Cooke
    -0.67
     arr
    -0.67
     avg
    -0.66
     guess
    -0.65
    POSITIVE LOGITS
     보
    0.88
    holdings
    0.85
     tabletas
    0.82
     côtés
    0.81
     listView
    0.80
     pastillas
    0.79
     iam
    0.79
     Phạm
    0.78
    listed
    0.77
     Sanz
    0.77
    Activations Density 0.032%

    No Known Activations