© 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. 102744
    Prev
    Next
    INDEX
    Explanations

    person/pronouns followed by verbs/auxiliaries

    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
    </h2>
    -1.86
     even
    -1.51
     melalui
    -1.41
     через
    -1.41
     bereits
    -1.40
     primero
    -1.39
     durch
    -1.38
     than
    -1.38
    ที่จะ
    -1.34
     where
    -1.34
    POSITIVE LOGITS
    ブーツ
    1.25
     endregion
    1.25
     cuillère
    1.21
    iiiii
    1.20
     vna
    1.20
     tén
    1.16
    之色
    1.16
     rechange
    1.15
     Suom
    1.15
    ването
    1.15
    Activations Density 0.043%

    No Known Activations