© 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. 3192
    Prev
    Next
    INDEX
    Explanations

    attributes describing domains or qualities

    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
     illustrates
    0.31
    appliquer
    0.31
     injective
    0.30
     *:
    0.29
    Hvis
    0.29
     applying
    0.29
     ஒவ்வொரு
    0.28
    如果要
    0.28
     Nếu
    0.28
     AttributeError
    0.28
    POSITIVE LOGITS
    -
    0.45
    /
    0.36
    性と
    0.35
     and
    0.33
    性和
    0.32
    -,
    0.32
     migrants
    0.31
     ও
    0.30
    -/
    0.27
     спорта
    0.27
    Activations Density 0.624%

    No Known Activations