© 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. 12639
    Prev
    Next
    INDEX
    Explanations

    .env files and dotenv

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

    The neuron fires strongly on references to hidden configuration files or environment variable paths (i.e. “.env,” “ZDOTDIR,” etc.).

    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
     jaan
    0.61
     밤
    0.58
     palp
    0.57
     night
    0.55
     winters
    0.55
     buddy
    0.54
    NEUTRON
    0.54
    ومات
    0.54
     psor
    0.54
    夜
    0.53
    POSITIVE LOGITS
    ibt
    0.66
    varepsilon
    0.59
    complex
    0.56
     семи
    0.55
    ಕು
    0.54
    వైపు
    0.54
    collection
    0.53
    chanted
    0.52
     Administração
    0.52
    <0x87>
    0.51
    Activations Density 0.000%

    No Known Activations