© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    social/media content and code snippets

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

    The neuron is strongly activated by words appearing right at the start of sentences (i.e. it marks sentence beginnings).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    userInput
    0.60
     quadratic
    0.56
    完璧
    0.56
    作业
    0.56
    geometric
    0.55
    wash
    0.55
     जवाहर
    0.55
    Ꮏ
    0.55
    quadratic
    0.55
    bubble
    0.54
    POSITIVE LOGITS
    </h4>
    0.56
     형태로
    0.56
     Social
    0.56
     социального
    0.55
     social
    0.55
     McPherson
    0.54
     SOCIAL
    0.54
     soziale
    0.54
    सोशल
    0.52
     enabled
    0.51
    Activations Density 0.004%

    No Known Activations