© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3824
    Prev
    Next
    INDEX
    Explanations

    lists of numbers

    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
     ۹
    0.21
     når
    0.20
     těch
    0.20
     eğer
    0.20
     ㅛ
    0.19
     आज
    0.19
     избежать
    0.19
    esseur
    0.19
    ４
    0.19
     někter
    0.19
    POSITIVE LOGITS
     separate
    0.27
     distinct
    0.25
     different
    0.24
    +
    0.23
    (!)
    0.21
     consecutive
    0.21
     (!)
    0.20
     contrasting
    0.19
     competing
    0.19
     standout
    0.19
    Activations Density 0.237%

    No Known Activations