© 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. 118810
    Prev
    Next
    INDEX
    Explanations

    at a time

    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
    affirm
    -0.88
    óval
    -0.82
     Kalam
    -0.80
     姜
    -0.79
     たま
    -0.77
     شيء
    -0.76
    aları
    -0.76
     仕事
    -0.75
    terse
    -0.74
     qualcosa
    -0.74
    POSITIVE LOGITS
     a
    2.55
     time
    2.05
    atime
    1.60
    time
    1.23
     fois
    1.13
     vez
    1.03
    getTime
    1.02
     Time
    1.00
    Time
    0.98
     समय
    0.94
    Activations Density 0.015%

    No Known Activations