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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75492
    Prev
    Next
    INDEX
    Explanations

    days and hours

    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
    땐
    -0.79
    Tonight
    -0.77
    flik
    -0.76
    影像
    -0.76
     ureter
    -0.75
     Nacht
    -0.72
    setTimeout
    -0.72
    𝘱
    -0.71
    ])))
    -0.71
    chure
    -0.70
    POSITIVE LOGITS
     Monday
    5.78
    Monday
    4.69
     monday
    3.64
     Tuesday
    3.44
    monday
    3.41
     MONDAY
    3.20
     Mondays
    3.13
     lundi
    2.95
    MONDAY
    2.67
    周一
    2.66
    Activations Density 0.093%

    No Known Activations