© 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. 110619
    Prev
    Next
    INDEX
    Explanations

    using code or technology

    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
     lavado
    0.37
     स्ट्रा
    0.37
     falsely
    0.36
     Neder
    0.36
    וא
    0.35
     قرمز
    0.34
    ಕ
    0.34
    ра
    0.34
     neder
    0.34
    quinazoline
    0.34
    POSITIVE LOGITS
     использует
    0.42
     Sử
    0.42
     utilise
    0.40
     THOR
    0.40
    getID
    0.40
     dic
    0.39
     論
    0.39
     Lel
    0.38
    dic
    0.38
     გამოყენ
    0.38
    Activations Density 0.000%

    No Known Activations