© 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. 90111
    Prev
    Next
    INDEX
    Explanations

    software version number

    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
    蛯
    -0.65
     sample
    -0.65
    maila
    -0.64
     nuôi
    -0.63
     seemingly
    -0.63
     COMPANY
    -0.63
    واف
    -0.62
    俳
    -0.62
     coldness
    -0.62
    dey
    -0.61
    POSITIVE LOGITS
     colspan
    0.88
     trở
    0.79
    )|\
    0.75
    يت
    0.74
    incl
    0.73
     mukaan
    0.71
    cfa
    0.71
    うちの
    0.70
    نی
    0.68
    Boas
    0.67
    Activations Density 0.135%

    No Known Activations