© 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. 40-GEMMASCOPE-2-RES-262K
    4. 736
    Prev
    Next
    INDEX
    Explanations

    code file paths and commands

    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_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
     Calyce
    0.20
     живело
    0.20
    踺
    0.19
    อม
    0.19
     коли
    0.19
    ClFN
    0.19
    衄
    0.19
     Ecusson
    0.18
    谒
    0.18
    ólica
    0.18
    POSITIVE LOGITS
     ~/.
    0.28
     $(
    0.26
     ssh
    0.25
     my
    0.24
     $
    0.24
    localhost
    0.23
    main
    0.23
     localhost
    0.22
    my
    0.22
     Linux
    0.21
    Activations Density 0.156%

    No Known Activations