© 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. 13846
    Prev
    Next
    INDEX
    Explanations

    weigh importance

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

    This neuron detects tokens that represent numeric or URL-like elements—e.g. years, volume/page numbers, and “https://” links often found in citations or 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_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
    ๕
    0.84
    ছিলো
    0.84
    Valve
    0.83
    DefaultFor
    0.81
    CTG
    0.81
    '},
    0.79
    ছিল
    0.78
    ZX
    0.77
     სახელმწიფო
    0.76
    ছিলাম
    0.75
    POSITIVE LOGITS
     spermatozoa
    0.82
     estrogen
    0.79
    
    0.78
     tulle
    0.77
    い
    0.75
     ≥
    0.73
     cioc
    0.70
    T
    0.70
    ς
    0.70
     roaming
    0.70
    Activations Density 0.001%

    No Known Activations