© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    Python Flask imports

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

    The neuron strongly activates on technical programming terms and file‐oriented code references (e.g., templates, views, models, Socket.io).

    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
    sim
    0.59
     অস্ট্রেল
    0.54
     sim
    0.52
     проте
    0.52
    semantics
    0.50
    Kh
    0.50
     convexes
    0.50
    ཧ
    0.50
     smoothness
    0.50
     impedances
    0.49
    POSITIVE LOGITS
     Flask
    1.61
     SQLAlchemy
    1.52
     flask
    1.51
    Flask
    1.51
    flask
    1.39
     sqlalchemy
    1.34
    SQLALCHEMY
    1.30
    sqlalchemy
    1.20
     flasks
    1.03
    FlaskApp
    1.03
    Activations Density 0.009%

    No Known Activations