© 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. 70597
    Prev
    Next
    INDEX
    Explanations

    how dare you

    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
    ஂ
    -2.67
     \
    -2.67
     faldas
    -2.50
    蛧
    -2.48
     joyas
    -2.45
    ୈ
    -2.44
    暂无
    -2.41
    i
    -2.28
    我来
    -2.27
    atação
    -2.27
    POSITIVE LOGITS
    硨
    3.13
     totalement
    2.72
     estavam
    2.61
     fizeram
    2.47
     faltan
    2.44
    是他
    2.41
    CHREIB
    2.39
     possui
    2.36
    が届
    2.36
     Vgl
    2.34
    Activations Density 0.002%

    No Known Activations