© 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. 30598
    Prev
    Next
    INDEX
    Explanations

    trading, integration, and development

    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
    ające
    0.83
    𝓾
    0.83
    ającej
    0.80
    ających
    0.79
    codewords
    0.78
    𝔀
    0.78
    委員會
    0.78
    wyczaj
    0.77
    𝓼
    0.77
    áciu
    0.76
    POSITIVE LOGITS
     ү
    1.19
     һәм
    1.13
     э
    1.13
     ө
    1.13
     о
    1.09
     һ
    1.09
     ә
    1.09
     а
    1.08
     та
    1.08
     сы
    1.08
    Activations Density 0.000%

    No Known Activations