© 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-65K
    7. 61625
    Prev
    Next
    INDEX
    Explanations

    even if casual

    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_65k_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
    秵
    0.50
     計算
    0.47
    addEnemy
    0.44
     أكثر
    0.44
     الأكثر
    0.44
    WEIGHT
    0.43
     ওজন
    0.43
     ಎಷ್ಟು
    0.42
     乾燥
    0.41
     Leaving
    0.41
    POSITIVE LOGITS
     being
    0.51
     poli
    0.45
     '
    0.44
     impuls
    0.41
     Being
    0.41
     było
    0.41
     gut
    0.40
     instincts
    0.40
    Being
    0.40
    elia
    0.39
    Activations Density 0.008%

    No Known Activations