© 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. 191728
    Prev
    Next
    INDEX
    Explanations

    hanging

    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
    陋
    0.39
     inscrição
    0.37
     सब्जेक्ट
    0.37
    elajaran
    0.37
    iotics
    0.37
    뀝
    0.37
     विषय
    0.36
     tabletop
    0.36
     রাজস্ব
    0.36
    keto
    0.36
    POSITIVE LOGITS
     hanger
    1.38
     hangers
    1.38
    挂
    1.31
     hanging
    1.24
     hang
    1.19
     Hanging
    1.16
     Hang
    1.11
    Hang
    1.09
     hanged
    1.09
    掛
    1.09
    Activations Density 0.015%

    No Known Activations