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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 246932
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cominc
    0.49
    лез
    0.48
    aży
    0.48
    モチーフ
    0.47
     francés
    0.47
    リスト
    0.46
    ियर्स
    0.46
    쨩
    0.46
     җи
    0.46
     insertar
    0.45
    POSITIVE LOGITS
    yc
    0.47
    grow
    0.45
    tw
    0.45
    some
    0.44
    log
    0.44
    bmc
    0.44
    ha
    0.43
    gam
    0.41
    las
    0.41
    vod
    0.41
    Activations Density 0.005%

    No Known Activations