© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10882
    Prev
    Next
    INDEX
    Explanations

    Human Centipede

    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_31_width_65k_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
    0.29
    .
    0.28
     param
    0.25
     romantic
    0.25
     interviews
    0.24
    }
    0.23
     ropes
    0.23
     ♥
    0.23
    。
    0.23
     emotional
    0.22
    POSITIVE LOGITS
    ျေး
    0.31
    虢
    0.28
    ຈັດສົ່ງ
    0.28
     تیاری
    0.26
     निजामा
    0.26
    鲔
    0.26
     उत्पादन
    0.26
    سباب
    0.26
    <unused1731>
    0.26
    ید
    0.25
    Activations Density 0.048%

    No Known Activations