© 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. 29797
    Prev
    Next
    INDEX
    Explanations

    according to

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

    reasons for actions

    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
    ༤
    0.50
    हमारे
    0.49
    鉐
    0.48
    缦
    0.46
     выбран
    0.45
     ಅಥವಾ
    0.45
    פרי
    0.44
    ৃতির
    0.43
    हमने
    0.43
    Новости
    0.43
    POSITIVE LOGITS
     Hurts
    0.52
     §
    0.51
     $
    0.48
     Be
    0.46
    heds
    0.46
    ham
    0.45
     (
    0.45
     Wex
    0.45
     They
    0.45
     dissatisfaction
    0.44
    Activations Density 0.000%

    No Known Activations