© 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. 191593
    Prev
    Next
    INDEX
    Explanations

    smells of disinfectant

    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
    Scopes
    0.39
     Fluids
    0.37
    睄
    0.37
     slowest
    0.36
    গায়
    0.36
     clav
    0.36
    রাত
    0.36
    喉
    0.36
     jedes
    0.35
    Fel
    0.34
    POSITIVE LOGITS
    лару
    0.40
    Ссы
    0.39
    drá
    0.39
     HOT
    0.38
    Talking
    0.37
     Ahí
    0.37
    ño
    0.37
    ίζει
    0.37
    ஶ
    0.36
    ڙ
    0.36
    Activations Density 0.000%

    No Known Activations