© 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. 210517
    Prev
    Next
    INDEX
    Explanations

    russian radio code

    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
    譯
    0.39
    Burns
    0.37
    ᓚ
    0.37
    ceans
    0.37
    }^{+}\
    0.36
     كات
    0.36
     কণ্
    0.36
    ElementException
    0.36
    mohan
    0.36
    ListenAnd
    0.36
    POSITIVE LOGITS
     б
    0.38
     OC
    0.38
     MORE
    0.38
     b
    0.38
     Saber
    0.38
     JACKSON
    0.37
     isom
    0.37
     g
    0.37
     gry
    0.37
     *_
    0.37
    Activations Density 0.000%

    No Known Activations