© 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. 40-GEMMASCOPE-2-RES-262K
    4. 224290
    Prev
    Next
    INDEX
    Explanations

    progress and roadblocks

    np_acts-logits-general · gemini-2.5-flash-lite

    It responds to rare or high-index vocabulary tokens—uncommon words that stand out in the token distribution.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ক্লাশ
    0.39
     xray
    0.39
     Вики
    0.38
    йон
    0.37
     گرف
    0.36
     troubles
    0.36
    йом
    0.36
     sadly
    0.35
     شکایت
    0.35
    ijker
    0.35
    POSITIVE LOGITS
    LError
    0.40
     معين
    0.40
     Mél
    0.39
     فونٹ
    0.38
    áneo
    0.38
    ;
    0.37
     কাছাকাছি
    0.37
     Protective
    0.36
     Noir
    0.35
    ‒
    0.35
    Activations Density 0.000%

    No Known Activations