© 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. 256611
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     personas
    0.46
    $[\
    0.46
    ע
    0.45
    i
    0.45
     Works
    0.44
    )\$(
    0.44
    suffixes
    0.44
    actors
    0.43
    人で
    0.43
    ي
    0.43
    POSITIVE LOGITS
     संबोध
    0.52
     вважа
    0.49
     مز
    0.49
     незавершена
    0.48
     vårt
    0.48
     цього
    0.47
     мі
    0.47
     نب
    0.47
     зо
    0.46
     எப்ப
    0.45
    Activations Density 0.000%

    No Known Activations