© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2416
    Prev
    Next
    INDEX
    Explanations

    #include <loan

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

    The neuron detects URL and file‐path elements—tokens like “http,” “://,” “www,” domain parts, slashes, and directory names.

    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_24_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
     Fleurit
    0.48
     distaste
    0.46
     separar
    0.44
    emies
    0.43
    ష్టం
    0.43
     flanges
    0.42
    🩸
    0.42
     HStack
    0.41
     neglig
    0.40
     unsatisf
    0.39
    POSITIVE LOGITS
     Christopher
    0.59
     Michael
    0.58
     George
    0.58
    G
    0.56
     Christian
    0.55
     Matthew
    0.54
    4
    0.54
    7
    0.52
    Y
    0.52
    8
    0.51
    Activations Density 1.159%

    No Known Activations