© 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. 120275
    Prev
    Next
    INDEX
    Explanations

    percentages, contractor, baby

    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
     refrained
    0.40
     stupid
    0.39
    ್ಯಾ
    0.39
    ជាមួយនឹង
    0.38
     withholding
    0.37
     προβ
    0.37
    chts
    0.36
     --->
    0.36
     パン
    0.36
     thinking
    0.36
    POSITIVE LOGITS
     இருப்பது
    0.37
    ự
    0.37
    xcscheme
    0.35
    するか
    0.35
    dur
    0.35
    যেমন
    0.35
    িৎ
    0.34
    するのは
    0.33
     Herren
    0.33
     নৈ
    0.33
    Activations Density 0.000%

    No Known Activations