© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103828
    Prev
    Next
    INDEX
    Explanations

    organizations and brands

    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_16_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
     (
    0.63
     the
    0.60
    t
    0.58
     coalition
    0.57
     in
    0.57
    ine
    0.57
     prestigious
    0.57
    </h6>
    0.55
    ```
    0.55
     tr
    0.54
    POSITIVE LOGITS
    Gamepad
    0.65
     جميع
    0.61
    কানিক্যাল
    0.59
    Przyp
    0.58
     zásobníku
    0.58
    Temperatura
    0.58
     كافة
    0.58
    ENABLE
    0.57
    Butyl
    0.57
     Kanban
    0.57
    Activations Density 0.005%

    No Known Activations