© 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. 188172
    Prev
    Next
    INDEX
    Explanations

    comparison, relationship, or action completion

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

    hybrid: a combination

    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
     protéger
    0.57
     proteger
    0.48
     décidé
    0.45
     ši
    0.45
     ஏற்கனவே
    0.45
     météor
    0.45
    乐
    0.45
     réussir
    0.44
     protección
    0.44
     métro
    0.43
    POSITIVE LOGITS
     where
    0.57
     SAMP
    0.55
     for
    0.52
     onde
    0.49
     butchers
    0.47
     吸
    0.47
    );
    0.46
     WHERE
    0.46
     KB
    0.46
    скому
    0.46
    Activations Density 0.001%

    No Known Activations