© 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. 135427
    Prev
    Next
    INDEX
    Explanations

    years, occurs, reactions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Га
    0.50
     meget
    0.45
     conseguiu
    0.44
    fters
    0.42
     muito
    0.42
     kuidas
    0.42
    \
    0.41
    Я
    0.41
     оригі
    0.41
    ʊ
    0.41
    POSITIVE LOGITS
    纤维
    0.51
    businesses
    0.50
    িল্প
    0.49
    regierung
    0.49
    из
    0.47
    irani
    0.45
    intentional
    0.44
     Businesses
    0.44
    Municipal
    0.44
    phthalm
    0.43
    Activations Density 0.006%

    No Known Activations