© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    organizing, organizations, organic

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

    The neuron responds to the character‐sequence “org,” whether in URLs (e.g. “org/”) or in words like “Organizing” or “Organizational,” i.e. it spots the “org” substring.

    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
    佑
    0.64
    Util
    0.63
     filepath
    0.57
    FieldError
    0.57
    Tag
    0.56
    uploader
    0.55
    ルーム
    0.54
    поте
    0.54
    喂
    0.54
    বিদ্যা
    0.53
    POSITIVE LOGITS
    springframework
    1.02
    apache
    1.02
    jetbrains
    0.93
    codehaus
    0.83
     apache
    0.82
    openqa
    0.76
    slf
    0.75
    eclipse
    0.73
    netbeans
    0.70
    jboss
    0.69
    Activations Density 0.066%

    No Known Activations