© 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. 3941
    Prev
    Next
    INDEX
    Explanations

    smoking cigarette

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

    This neuron is essentially a positional‐index detector: it fires in proportion to how far you are through the document, i.e. it tracks token position.

    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
    tg
    0.81
    t
    0.81
    conto
    0.79
    ma
    0.74
     потім
    0.73
    tay
    0.71
    mi
    0.71
    mlung
    0.70
    boleh
    0.70
    tal
    0.69
    POSITIVE LOGITS
     BBS
    0.80
     Brands
    0.79
     Dreams
    0.77
    istanbul
    0.75
     CORS
    0.74
    著
    0.73
     BMS
    0.72
     καὶ
    0.70
     HIIT
    0.70
     IBS
    0.70
    Activations Density 0.001%

    No Known Activations