© 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. 119281
    Prev
    Next
    INDEX
    Explanations

    cleaning electronics

    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
     Knudsen
    0.37
    জ
    0.35
    發現
    0.35
     Norden
    0.35
    广州
    0.35
    London
    0.34
    时间
    0.33
    BOOKS
    0.33
    MADE
    0.33
     volume
    0.33
    POSITIVE LOGITS
    轢
    0.46
     tuh
    0.45
    ائق
    0.44
     electrónicos
    0.43
     አይደለም
    0.43
     അനുവദ
    0.43
     služ
    0.42
     HOWEVER
    0.42
     vaikka
    0.42
     পরিষ্কার
    0.41
    Activations Density 0.001%

    No Known Activations