© 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. 8216
    Prev
    Next
    INDEX
    Explanations

    change types, start dates

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

    This neuron is effectively inactive (a “dead” neuron that never responds to any tokens).

    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
    ق
    0.76
    Conflict
    0.72
    Jimmy
    0.70
     журнала
    0.70
    का
    0.69
    スカート
    0.67
    циона
    0.66
     дорого
    0.66
    рование
    0.64
    мино
    0.64
    POSITIVE LOGITS
    ﻱ
    0.92
     dominance
    0.89
    nt
    0.85
    descriptors
    0.84
    recipes
    0.83
    rk
    0.82
    lus
    0.82
    tpc
    0.82
    rett
    0.80
    nti
    0.78
    Activations Density 0.001%

    No Known Activations