© 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. 10-GEMMASCOPE-RES-131K
    7. 67156
    Prev
    Next
    INDEX
    Explanations

    Thai and Devanagari 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_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
     mutta
    -2.77
    縷
    -2.52
    2
    -2.52
    あります
    -2.48
    方がいい
    -2.28
     nhưng
    -2.27
     Bedürfn
    -2.20
    śmy
    -2.19
     вроде
    -2.19
     besonderen
    -2.17
    POSITIVE LOGITS
    我
    2.38
    镦
    2.31
     «
    2.14
    >
    2.14
    (
    2.09
    или
    2.08
    j
    2.06
     â
    2.05
    „
    2.05
    /"
    2.03
    Activations Density 0.000%

    No Known Activations