© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19933
    Prev
    Next
    INDEX
    Explanations

    shapes and connections

    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
     구조
    0.47
     સરકાર
    0.46
    权威
    0.42
     úč
    0.42
     리그
    0.41
     프로그램
    0.41
    換
    0.41
     정책
    0.41
    ोत
    0.41
    patri
    0.40
    POSITIVE LOGITS
    entgen
    0.43
    ellipse
    0.43
     intestine
    0.39
     apparently
    0.39
    ♌
    0.39
     between
    0.39
     condensers
    0.38
    setopt
    0.38
     протя
    0.38
    膀
    0.38
    Activations Density 0.008%

    No Known Activations