© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189986
    Prev
    Next
    INDEX
    Explanations

    foreign language text segments

    np_acts-logits-general · gemini-2.5-flash-lite

    color blind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cytoplasm
    0.45
    ILL
    0.44
     as
    0.43
    sd
    0.42
    QTY
    0.42
    my
    0.41
    MOTION
    0.41
    只
    0.41
    passport
    0.41
     households
    0.40
    POSITIVE LOGITS
    चलित
    0.56
     कंडक्टर
    0.56
     दिवंगत
    0.53
     நிகழ்ச்ச
    0.52
    ంలో
    0.52
     özelliği
    0.51
     aidant
    0.51
    ضای
    0.50
     disebabkan
    0.50
     réfl
    0.49
    Activations Density 0.000%

    No Known Activations