© 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. 31749
    Prev
    Next
    INDEX
    Explanations

    Zulu and Nobel Peace Prize

    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
     Gretchen
    0.41
    তান্ত্রিক
    0.40
     obrá
    0.40
    [:
    0.39
     Calder
    0.39
     অঙ্গীকার
    0.39
    馨
    0.38
    谌
    0.38
    家の
    0.38
    dit
    0.38
    POSITIVE LOGITS
     KwaZulu
    1.07
     Durban
    0.96
    Zulu
    0.81
     Zulu
    0.79
    Kwa
    0.68
    Natal
    0.65
     QString
    0.64
     Natal
    0.61
     Zul
    0.60
     Queensland
    0.57
    Activations Density 0.002%

    No Known Activations