© 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. 3027
    Prev
    Next
    INDEX
    Explanations

    ```json` or math notation

    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
    3
    0.45
     configur
    0.43
    !),
    0.41
     revoc
    0.41
     esper
    0.40
    ലം
    0.40
     enlarg
    0.40
     interven
    0.39
    !).
    0.39
     रखा
    0.39
    POSITIVE LOGITS
    uları
    0.52
     ，
    0.48
    uaire
    0.47
     的
    0.43
    Đối
    0.41
     Pokud
    0.41
     Thay
    0.41
    Chúng
    0.41
     อาจ
    0.40
    lijah
    0.40
    Activations Density 0.063%

    No Known Activations