© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40968
    Prev
    Next
    INDEX
    Explanations

    reject / module / concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    시
    0.49
    Fecha
    0.46
    體
    0.46
    いた
    0.45
    Thro
    0.45
    就
    0.45
    τα
    0.45
    ताल
    0.44
    물
    0.43
    보
    0.43
    POSITIVE LOGITS
    lak
    0.47
     anthropology
    0.46
     elektrom
    0.46
     astrophys
    0.45
     anthropologists
    0.44
     Ok
    0.44
     köy
    0.43
    nap
    0.43
     pst
    0.43
     जादू
    0.43
    Activations Density 0.001%

    No Known Activations