© 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. 119472
    Prev
    Next
    INDEX
    Explanations

    multiple, heavily modified, data, hazard, freighter

    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
     nerdy
    0.39
    Daddy
    0.38
    ϻ
    0.38
    ٹرز
    0.38
     हमने
    0.38
    ゃ
    0.37
     wanna
    0.37
    ‌پ
    0.37
    Yay
    0.37
    Fear
    0.36
    POSITIVE LOGITS
    ෝග
    0.37
     ইস্ট
    0.37
     accomplishments
    0.36
     নারায়ণ
    0.36
     acord
    0.36
    =$(
    0.36
     prestations
    0.35
     conditions
    0.35
     न्याया
    0.35
     trayectoria
    0.35
    Activations Density 0.002%

    No Known Activations