© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1392
    Prev
    Next
    INDEX
    Explanations

    like and as for comparisons

    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_40_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
     surtout
    0.23
     Added
    0.22
     、
    0.22
     Announces
    0.22
    （
    0.22
     incluindo
    0.22
    ↵↵
    0.21
    、
    0.21
    。
    0.21
     incluyendo
    0.20
    POSITIVE LOGITS
     we
    0.36
     आपण
    0.34
     you
    0.30
     было
    0.30
     they
    0.29
     любят
    0.29
     ocurre
    0.29
     it
    0.29
     happened
    0.28
     bạn
    0.28
    Activations Density 0.045%

    No Known Activations