© 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. 10-GEMMASCOPE-RES-131K
    7. 12250
    Prev
    Next
    INDEX
    Explanations

    v

    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_10/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
    茈
    -1.85
     kompati
    -1.76
     you
    -1.74
     kamer
    -1.73
    щихся
    -1.70
    loir
    -1.70
     vuitton
    -1.69
    鼯
    -1.67
     astuces
    -1.66
    艄
    -1.64
    POSITIVE LOGITS
    on
    1.93
     when
    1.93
    d
    1.74
     shows
    1.62
    で
    1.61
     in
    1.55
     Bereichen
    1.54
     "
    1.54
    k
    1.52
     Fällen
    1.44
    Activations Density 0.002%

    No Known Activations