© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    URLs and codes

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

    This neuron detects short mixed‐case alphanumeric strings that appear as link identifiers in URLs (e.g., YouTube or bit.ly codes).

    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
    8
    0.68
    Sub
    0.61
    Oops
    0.60
    SUB
    0.59
    ACCOUNT
    0.58
    9
    0.58
    (=
    0.57
    หย
    0.56
    UNDER
    0.55
     %><%=
    0.54
    POSITIVE LOGITS
    ត្
    0.66
     Лі
    0.64
     chois
    0.64
     choisi
    0.61
     théâtre
    0.61
     parka
    0.59
     común
    0.59
     willow
    0.59
     cvec
    0.58
     puertas
    0.57
    Activations Density 0.010%

    No Known Activations