© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4227
    Prev
    Next
    INDEX
    Explanations

    standing desk debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     deň
    1.47
     hẹn
    1.41
    এ
    1.35
    😍
    1.34
     ולא
    1.31
    
    1.30
    魏
    1.29
     máu
    1.28
    <0xBE>
    1.27
    га
    1.27
    POSITIVE LOGITS
    ség
    1.53
     dasar
    1.45
     cuyos
    1.45
     distinguir
    1.44
     creemos
    1.43
     strikingly
    1.40
    기와
    1.39
    ों
    1.38
     pasando
    1.38
    دت
    1.34
    Activations Density 0.001%

    No Known Activations