© 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. 244281
    Prev
    Next
    INDEX
    Explanations

    word or phrase

    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
     आध्यात्म
    0.53
     आध्यात्मिक
    0.52
     plaf
    0.49
     அளவிற்கு
    0.48
     creeks
    0.47
    =>
    0.46
    ]*
    0.46
     ఎన్ని
    0.46
     زاويه
    0.46
     gneiss
    0.46
    POSITIVE LOGITS
    igia
    0.52
    ’
    0.51
     Computation
    0.50
    ipasi
    0.44
    ikä
    0.44
     was
    0.43
     Educator
    0.43
    Computation
    0.40
     lysis
    0.40
    шти
    0.39
    Activations Density 0.000%

    No Known Activations