© 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. 133468
    Prev
    Next
    INDEX
    Explanations

    Power Distance (PDI)

    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
    ☑
    0.40
     किशन
    0.38
     दस्तावेजों
    0.38
     ✅
    0.37
    UWORD
    0.37
     بدأ
    0.36
    什么样的
    0.36
    Document
    0.36
     polyester
    0.35
     документа
    0.35
    POSITIVE LOGITS
    ≤</
    0.43
    今後の
    0.41
    रु
    0.40
     successes
    0.39
    今後
    0.38
     অচ
    0.38
    सल
    0.37
    <unused34>
    0.37
    uacute
    0.37
    aurus
    0.37
    Activations Density 0.000%

    No Known Activations