© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8949
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units like minutes, hours, or seconds

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

    The neuron fires on job‐title words (e.g. “manager”).

    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
     가는
    0.71
    전
    0.70
    Located
    0.68
    зим
    0.68
     сво
    0.68
    withProperties
    0.68
     ње
    0.67
     църква
    0.66
    ارو
    0.66
     Contact
    0.65
    POSITIVE LOGITS
    𝘨
    0.88
    citizen
    0.88
    postos
    0.85
    gaussian
    0.84
    मॉन
    0.84
    ueroa
    0.82
    ंदोल
    0.82
    EMPT
    0.80
    pea
    0.80
    鳅
    0.79
    Activations Density 0.000%

    No Known Activations