© 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. 31-GEMMASCOPE-2-RES-65K
    7. 53188
    Prev
    Next
    INDEX
    Explanations

    biological processes, physics concepts

    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
     또는
    0.68
    または
    0.52
     appreciation
    0.51
    หรือ
    0.50
     yoki
    0.50
    或
    0.50
     ಮತ್ತು
    0.50
     veya
    0.50
     یا
    0.49
     ಅಥವಾ
    0.49
    POSITIVE LOGITS
    нице
    0.47
     miliardi
    0.46
    揣
    0.42
     counties
    0.40
     targeting
    0.40
     scegli
    0.40
     lobbyists
    0.40
     কোম্পানির
    0.38
    ڙ
    0.38
    uggish
    0.38
    Activations Density 0.019%

    No Known Activations