© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211484
    Prev
    Next
    INDEX
    Explanations

    manual gearbox

    np_acts-logits-general · gemini-2.5-flash-lite

    Fake DOB

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    র্গে
    0.48
    ேஷ்
    0.47
    データを
    0.47
     université
    0.46
    طور
    0.46
     procéd
    0.45
     fluctuates
    0.44
    狍
    0.44
    𝕦
    0.44
     결방
    0.44
    POSITIVE LOGITS
    0.45
    cond
    0.45
     linen
    0.44
     која
    0.44
     VIH
    0.44
     Yeti
    0.43
    nta
    0.43
    ;
    0.43
     Э
    0.43
     Xmas
    0.41
    Activations Density 0.002%

    No Known Activations