© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6286
    Prev
    Next
    INDEX
    Explanations

    wp-admin and uploads

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

    This neuron detects PHP runtime warning/error messages (e.g. “Use of undefined constant,” “Undefined offset,” file path and line-number references).

    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
    зульта
    0.64
    mington
    0.60
    꽈
    0.60
     সুদ
    0.58
    怯
    0.56
    Kitty
    0.56
     Kitty
    0.55
    hovah
    0.55
     congrats
    0.55
     рублей
    0.54
    POSITIVE LOGITS
    アプリケーション
    0.66
     Applications
    0.65
    Applications
    0.63
     APPLICATIONS
    0.63
     APPLICATION
    0.63
    负载
    0.60
     objek
    0.58
    ENGINE
    0.58
    應用
    0.58
    <0x0F>
    0.57
    Activations Density 0.024%

    No Known Activations