© 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. 118695
    Prev
    Next
    INDEX
    Explanations

    specific times and intervals

    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
     dnia
    -0.74
    Maximize
    -0.72
    Categorie
    -0.72
    国王
    -0.69
    べて
    -0.68
    كويكب
    -0.68
    ಂದ
    -0.68
     rout
    -0.67
     Maximum
    -0.67
     Rout
    -0.66
    POSITIVE LOGITS
     hour
    2.00
     hourly
    1.56
    Hour
    1.56
    hour
    1.50
     Hour
    1.42
     quarter
    1.42
    hourly
    1.36
     HOUR
    1.32
     stroke
    1.23
    quarter
    1.16
    Activations Density 0.023%

    No Known Activations