© 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. 64496
    Prev
    Next
    INDEX
    Explanations

    safety and harm

    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
    ST
    0.46
    7
    0.45
    da
    0.40
    Restaurant
    0.39
    P
    0.39
    B
    0.38
    ada
    0.38
    Juan
    0.38
    備
    0.38
    深受
    0.37
    POSITIVE LOGITS
     थी
    0.53
     تھی
    0.52
     destru
    0.50
    <unused14>
    0.46
     ट्रे
    0.46
    horror
    0.46
     ክ
    0.45
     Unterschiede
    0.45
     ክፍል
    0.45
     horror
    0.44
    Activations Density 0.026%

    No Known Activations