© 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. 98769
    Prev
    Next
    INDEX
    Explanations

    what triggers needs

    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
     toko
    0.40
     strlen
    0.40
     শ্
    0.40
    雁
    0.39
     $\%
    0.39
     દિવસે
    0.38
    叒
    0.38
    িকাংশ
    0.37
    ogén
    0.36
    ဉ
    0.36
    POSITIVE LOGITS
    mers
    0.41
     USP
    0.38
     অস্ত্র
    0.38
    กับ
    0.36
     Jawah
    0.36
     Herbs
    0.36
    ment
    0.36
     cocktail
    0.35
     Diabetes
    0.34
     High
    0.34
    Activations Density 0.001%

    No Known Activations