© 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. 14672
    Prev
    Next
    INDEX
    Explanations

    German adjectivesGerman participlesbecome obviouscompany suffixesbecome apparentGoogle automotiveor lichen

    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
    鋱
    -2.34
    replyreport
    -2.33
     eventdata
    -2.33
    いって
    -2.31
    濵
    -2.25
     ваш
    -2.22
    佧
    -2.20
    ᠌
    -2.19
     shouldn
    -2.17
    fledged
    -2.13
    POSITIVE LOGITS
     lustig
    2.34
      
    2.34
    棡
    2.30
    <i>
    2.19
     {
    2.14
     spannend
    2.13
    ￪
    2.00
    ING
    1.98
     Kontext
    1.95
     hilfre
    1.95
    Activations Density 0.000%

    No Known Activations