© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3951
    Prev
    Next
    INDEX
    Explanations

    URLs and brand names

    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
    医療
    0.34
     vedno
    0.30
     nasceu
    0.29
    筺
    0.29
    ավ
    0.28
    醫療
    0.28
     inimes
    0.28
    塬
    0.27
    Rad
    0.27
    दर्शक
    0.27
    POSITIVE LOGITS
     fruct
    0.30
     fruitful
    0.29
     specific
    0.29
     faire
    0.29
    具体
    0.29
     superposition
    0.29
     feliz
    0.28
     these
    0.28
     affair
    0.28
     $
    0.28
    Activations Density 0.045%

    No Known Activations