© 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. 13687
    Prev
    Next
    INDEX
    Explanations

    child node

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

    The neuron activates on word fragments that end with a trailing hyphen (i.e. the first part of a hyphenated word).

    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
     […]
    0.53
    危机
    0.53
    5
    0.52
    […]
    0.49
     Labs
    0.49
    వీ
    0.48
    \\
    0.48
    FO
    0.48
    Guardian
    0.47
     Radiology
    0.47
    POSITIVE LOGITS
    髗
    0.53
    土産
    0.52
     WILSON
    0.51
     Чар
    0.51
     muffled
    0.51
    itivo
    0.50
     লইয়া
    0.50
    爐
    0.50
    ská
    0.49
     postul
    0.49
    Activations Density 0.001%

    No Known Activations