© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    influences starting

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

    The neuron is highly sensitive to mentions of handmade fabric craft projects or items (e.g. quilts, table runners, cushions).

    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
     […]
    0.49
    […]
    0.49
     (...
    0.43
    <unused2206>
    0.42
     (...)
    0.41
    <eos>
    0.40
    ,...
    0.40
    WASHINGTON
    0.39
    <unused2180>
    0.39
    GitHub
    0.39
    POSITIVE LOGITS
     piu
    0.85
     yg
    0.80
    ㄉ
    0.77
     tambien
    0.75
     đc
    0.74
     icin
    0.74
     बच्चो
    0.73
    ॔
    0.73
     महिलाओ
    0.71
     nao
    0.68
    Activations Density 1.626%

    No Known Activations