© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84393
    Prev
    Next
    INDEX
    Explanations

    bring lunch

    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
    бия
    -0.80
    lation
    -0.77
    lations
    -0.74
    atively
    -0.73
    紹
    -0.71
    坩
    -0.69
    กำ
    -0.68
     Liberation
    -0.68
     fiery
    -0.66
    lla
    -0.65
    POSITIVE LOGITS
     lunch
    2.98
     lunches
    2.86
     Lunch
    2.34
    Lunch
    2.28
    lunch
    2.11
     LUNCH
    1.84
     lunchtime
    1.81
     sandwich
    1.78
     sandwiches
    1.72
     Lun
    1.65
    Activations Density 0.020%

    No Known Activations