© 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. 10001
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on relatively uncommon or high-information content words (e.g. “third,” “various,” “distinguish”).

    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
    していました
    0.73
    icing
    0.70
     Lata
    0.70
    い
    0.69
    っていました
    0.68
    izawa
    0.67
     Dai
    0.65
    рое
    0.65
    romat
    0.65
    ument
    0.64
    POSITIVE LOGITS
     аба
    0.66
     जीतकर
    0.65
     cương
    0.63
     આપ
    0.59
    춰
    0.59
     ولم
    0.59
     яку
    0.59
    🔉
    0.59
    ĵo
    0.58
     समझौ
    0.57
    Activations Density 0.000%

    No Known Activations