© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64952
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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_22/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
     where
    -1.01
    цкого
    -0.81
     This
    -0.81
    codable
    -0.77
    ัท
    -0.76
    ilon
    -0.76
    kém
    -0.75
     …
    -0.75
     spac
    -0.74
    負荷
    -0.74
    POSITIVE LOGITS
    ;</
    0.91
    لكن
    0.90
    ΠΟ
    0.90
     eenig
    0.90
    锨
    0.89
    䨻
    0.88
     ucap
    0.88
    LEY
    0.86
    setLong
    0.86
    mathrm
    0.85
    Activations Density 0.204%

    No Known Activations