© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 234944
    Prev
    Next
    INDEX
    Explanations

    the token "voxel" (references to voxel variables in code).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    アイドル
    0.50
     منتقل
    0.47
    鐪
    0.42
    नून
    0.41
    HOUT
    0.41
    უთ
    0.40
    𝗿
    0.40
    学習
    0.40
    अप्रैल
    0.40
    𝙧
    0.39
    POSITIVE LOGITS
     Physics
    0.51
     Ali
    0.43
    Physics
    0.43
    veli
    0.43
    eni
    0.41
     फिजिक्स
    0.40
     physics
    0.40
    ì
    0.39
    териа
    0.38
     Corporal
    0.38
    Activations Density 0.000%

    No Known Activations