© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13743
    Prev
    Next
    INDEX
    Explanations

    new or existing people and capabilities

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

    The neuron fires on references to a team’s personnel makeup—words and phrases about groups of players, rosters, and practice squads.

    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
     civilizations
    0.69
     periodical
    0.64
    "/>.
    0.64
     periodically
    0.63
    其他
    0.61
     closely
    0.59
     neighboring
    0.59
     lifespan
    0.59
    ളാ
    0.59
    <unused2221>
    0.59
    POSITIVE LOGITS
     baru
    0.93
     novos
    0.89
     новую
    0.89
     csapat
    0.88
     nuevos
    0.84
     sepen
    0.84
     новый
    0.82
     новых
    0.82
     kekuatan
    0.82
     новом
    0.82
    Activations Density 0.067%

    No Known Activations