© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21380
    Prev
    Next
    INDEX
    Explanations

    as a

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

    Tokens that are part of the model/assistant's replies—especially the opening and content words of long assistant responses.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    Detects model/assistant-generated reply text — the start of the assistant's response (first‑person/model utterances).

    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
     ನಡುವ
    0.39
    的很
    0.37
    有两种
    0.36
     目前
    0.36
     hàm
    0.35
    ELSE
    0.35
     भागीदारों
    0.34
     मंत्रिमंडल
    0.34
    /***/
    0.33
    ันทร์
    0.33
    POSITIVE LOGITS
    作为
    2.03
     sebagai
    1.91
     Sebagai
    1.83
    作为一个
    1.81
    作為
    1.80
     作为
    1.80
    身为
    1.80
    Sebagai
    1.63
     selaku
    1.57
     jako
    1.56
    Activations Density 0.026%

    No Known Activations