© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35346
    Prev
    Next
    INDEX
    Explanations

    let bindings and code structures

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     veamos
    0.44
     Veamos
    0.43
     $+
    0.40
     затем
    0.39
     불구
    0.38
     digamos
    0.38
     następnie
    0.37
     anticon
    0.37
     subtração
    0.37
     $=\
    0.37
    POSITIVE LOGITS
     Counter
    0.37
    mohan
    0.36
     വൈ
    0.36
    rpt
    0.36
    lein
    0.36
    aigne
    0.36
    ards
    0.35
    みの
    0.35
    𝔦
    0.35
    isco
    0.34
    Activations Density 0.000%

    No Known Activations