© 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. 31-GEMMASCOPE-2-RES-262K
    4. 7830
    Prev
    Next
    INDEX
    Explanations

    actually

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

    The neuron detects strongly assertive or contrastive words and tokens that signal emphasis, certainty, or negation (e.g., “is/’s”, “isn’t/aren’t”, “almost”, “definitely”, “but”).

    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_31_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
    ופ
    0.39
     asimismo
    0.37
    들과
    0.36
     useParams
    0.35
     lợi
    0.35
    ゲル
    0.34
    ወስ
    0.34
    鿉
    0.34
    okkal
    0.34
     dược
    0.33
    POSITIVE LOGITS
     actually
    0.86
     Actually
    0.86
    actually
    0.83
    其實
    0.78
    其实
    0.77
     aslında
    0.74
    Actually
    0.74
     sebenarnya
    0.73
    実際
    0.72
    实际上
    0.64
    Activations Density 0.167%

    No Known Activations