© 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. 149513
    Prev
    Next
    INDEX
    Explanations

    consultations, analysing, shutdown, compiled, live

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

    fine-tuning, understanding, authority, neurofeedback, conditional statements

    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
    ธุรกิจ
    0.51
    Repl
    0.51
    ீ
    0.45
    RE
    0.45
    '
    0.45
    Don
    0.45
     jurídico
    0.45
    ตรา
    0.45
    ท
    0.43
    Ticket
    0.42
    POSITIVE LOGITS
    儩
    0.53
     ");
    0.50
     எவ்வளவு
    0.48
     Fitz
    0.48
    →</
    0.47
    hattis
    0.47
     ď
    0.47
     পাওয়
    0.46
    お願いします
    0.46
     raat
    0.46
    Activations Density 0.000%

    No Known Activations