© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123266
    Prev
    Next
    INDEX
    Explanations

    Xiao Li, even numbers, middle pivots

    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
    нали
    0.51
    Congratulations
    0.50
    لية
    0.46
     thiệt
    0.46
    邕
    0.46
     бойынша
    0.45
    ين
    0.45
    krét
    0.45
     રહી
    0.44
    扃
    0.44
    POSITIVE LOGITS
     sociological
    0.44
     differently
    0.44
     recession
    0.44
    ewer
    0.43
     cares
    0.43
     यू
    0.43
     splendid
    0.42
     bettors
    0.42
     meditate
    0.42
     restless
    0.41
    Activations Density 0.007%

    No Known Activations