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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48423
    Prev
    Next
    INDEX
    Explanations

    hour time hora horário

    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
    ：“……”
    -0.79
    mond
    -0.72
    킷
    -0.72
    veland
    -0.69
    lotte
    -0.69
    тистика
    -0.69
    Haz
    -0.69
    ulatory
    -0.68
     divisible
    -0.68
     Fibonacci
    -0.67
    POSITIVE LOGITS
     hour
    5.97
    hour
    4.59
     Hour
    4.22
    Hour
    4.09
     hours
    4.09
     HOUR
    3.50
     hora
    3.50
    HOUR
    3.41
     Hours
    3.09
    hours
    2.88
    Activations Density 0.028%

    No Known Activations