© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13963
    Prev
    Next
    INDEX
    Explanations

    numbered lists, bullet points

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

    The neuron primarily detects occurrences of direct second-person address (e.g. “you” and related pronouns) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ților
    0.59
    idone
    0.57
    ڽ
    0.57
    nsic
    0.56
    gles
    0.56
    țele
    0.55
    ọng
    0.54
    adrenergic
    0.54
    keyup
    0.54
    rikes
    0.54
    POSITIVE LOGITS
     again
    0.54
    <eos>
    0.52
     opět
    0.51
     finne
    0.50
     yine
    0.50
     noticeable
    0.49
     interviewee
    0.49
     remarqué
    0.48
     প্রথমে
    0.47
     tandis
    0.46
    Activations Density 0.026%

    No Known Activations