© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7741
    Prev
    Next
    INDEX
    Explanations

    "I" followed by punctuation or common verbs

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

    The neuron detects the first-person pronoun "I" (especially when used by the speaker at the start of utterances).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ли
    3.75
    م
    2.44
    ن
    2.42
    可以
    2.38
    ת
    2.19
    m
    2.14
    ند
    2.11
    و
    2.11
    nk
    2.06
    ا
    1.98
    POSITIVE LOGITS
    いた
    1.70
     виправивши
    1.57
    पूर्ण
    1.55
    toadd
    1.52
     kinerja
    1.45
    mobilpay
    1.42
    ϲ
    1.41
    ção
    1.39
    ("-"*
    1.39
    gesamt
    1.38
    Activations Density 0.541%

    No Known Activations