© 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. 224426
    Prev
    Next
    INDEX
    Explanations

    to real people

    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
     copia
    0.43
    étant
    0.42
    وْ
    0.41
     copiar
    0.41
     aquele
    0.39
    讵
    0.39
     compromet
    0.39
     исход
    0.38
    果
    0.38
    
    0.38
    POSITIVE LOGITS
     กำ
    0.43
     Named
    0.36
    व्या
    0.35
    กำ
    0.34
    പാട
    0.34
    भीर
    0.33
    KET
    0.33
    speople
    0.33
    เศ
    0.32
    คม
    0.32
    Activations Density 0.000%

    No Known Activations