© 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. 198366
    Prev
    Next
    INDEX
    Explanations

    great for

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

    non-english characters or words

    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
     projects
    0.49
    &&(
    0.45
     groups
    0.45
     projets
    0.44
    GRAY
    0.44
    ﺩ
    0.44
     Groups
    0.44
    ﻳ
    0.44
    ,(
    0.43
    Evalu
    0.43
    POSITIVE LOGITS
     nascetur
    0.50
    рії
    0.50
    рия
    0.49
    τικής
    0.48
     bicovariant
    0.45
    בוע
    0.45
     aran
    0.45
    틱
    0.45
     barre
    0.44
    ต้น
    0.44
    Activations Density 0.002%

    No Known Activations