© 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. 80981
    Prev
    Next
    INDEX
    Explanations

    scan banners quickly

    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
    드
    0.50
    qualified
    0.46
    Real
    0.46
    лан
    0.42
    Rhe
    0.41
    ceeded
    0.41
     everyone
    0.40
    Sole
    0.40
     its
    0.40
     mankind
    0.40
    POSITIVE LOGITS
     ""}
    0.54
     finanzi
    0.52
     einfacher
    0.47
     poteva
    0.46
     შეიძ
    0.46
    這些
    0.45
     souvent
    0.45
     Purchaser
    0.45
     którzy
    0.45
     produse
    0.45
    Activations Density 0.007%

    No Known Activations