© 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. 197782
    Prev
    Next
    INDEX
    Explanations

    promised, Rivals, TTY

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

    brightness, absorbs, power, efficiency

    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
     Рі
    0.53
    舀
    0.53
     Дом
    0.52
    Drive
    0.50
     всіх
    0.49
     бонусу
    0.49
     ڈپاز
    0.49
     питань
    0.49
     бк
    0.48
     پوچھ
    0.48
    POSITIVE LOGITS
     sublim
    0.51
     is
    0.51
     host
    0.48
     but
    0.48
     prior
    0.47
     \
    0.47
     current
    0.47
     stabil
    0.46
     vict
    0.46
     UX
    0.46
    Activations Density 0.000%

    No Known Activations