© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    specific criteria or categories

    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
     sklad
    0.46
    。
    0.44
     boolean
    0.44
    Scr
    0.42
    _"
    0.42
    ইন্দ
    0.42
     hacker
    0.42
     schm
    0.42
     logement
    0.41
     garage
    0.41
    POSITIVE LOGITS
    yyam
    0.46
    شود
    0.45
    catching
    0.45
    apped
    0.45
    カリ
    0.45
    oxides
    0.44
    dni
    0.44
    ಿಕ
    0.43
    d
    0.43
    rivi
    0.42
    Activations Density 0.000%

    No Known Activations