© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112432
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people or groups

    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
     henvis
    -1.45
     here
    -1.29
     a
    -1.29
    oreille
    -1.23
    螄
    -1.22
     красивый
    -1.21
     fonctionner
    -1.20
    Timo
    -1.19
    感じです
    -1.18
     gewähr
    -1.17
    POSITIVE LOGITS
     whom
    1.67
     of
    1.36
     with
    1.36
    ၄
    1.35
     whose
    1.34
    struzioni
    1.31
    Поэтому
    1.30
     which
    1.30
     glede
    1.28
     those
    1.27
    Activations Density 0.012%

    No Known Activations