© 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. 1220
    Prev
    Next
    INDEX
    Explanations

    variable assignments

    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
    Negative Logits
     உலோக
    0.30
    ሳሪያ
    0.27
    ತಕ್ಕ
    0.27
    疾患
    0.26
    utiérrez
    0.26
    कोलॉजी
    0.26
    髂
    0.26
     எல்லா
    0.25
     रिचार्ज
    0.25
     ಮಾಹಿತ
    0.25
    POSITIVE LOGITS
    -
    0.40
     (
    0.36
    :
    0.35
    /
    0.35
     and
    0.34
    _
    0.34
    +
    0.33
    ↵
    0.32
    ات
    0.32
    =
    0.32
    Activations Density 0.242%

    No Known Activations