© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    names followed by verbs

    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
    Negative Logits
    çal
    0.46
    '+
    0.42
    瞩
    0.41
     hegemony
    0.41
    ene
    0.40
    cier
    0.40
     ಪ್ರ
    0.39
    ża
    0.39
     havoc
    0.39
     instinctively
    0.39
    POSITIVE LOGITS
     ViewController
    0.50
     FileManager
    0.48
     Managed
    0.43
    𝐽
    0.43
     Ré
    0.42
     Δ
    0.42
     Marquette
    0.41
     ആവശ്യമ
    0.41
    在该
    0.41
     ∆
    0.40
    Activations Density 0.003%

    No Known Activations