© 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. 65928
    Prev
    Next
    INDEX
    Explanations

    walked through

    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
    Land
    0.46
     Land
    0.44
    Landau
    0.44
    ژن
    0.43
     adentro
    0.42
    陆
    0.42
    alignParent
    0.41
    陸
    0.41
     réduite
    0.41
    WithOwner
    0.41
    POSITIVE LOGITS
     SR
    0.48
    ეკ
    0.46
     sr
    0.44
     hold
    0.43
     conventional
    0.43
     CM
    0.42
     encyclopedia
    0.41
     Cuc
    0.41
    host
    0.41
     blanket
    0.41
    Activations Density 0.000%

    No Known Activations