© 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. 9017
    Prev
    Next
    INDEX
    Explanations

    The neuron flags unusually rare or low‐frequency content words.

    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
    s
    0.96
     handicapped
    0.84
     recomp
    0.80
    덫
    0.78
    터를
    0.77
    olive
    0.75
     vanqu
    0.75
    썬
    0.74
     treacherous
    0.73
     dainty
    0.72
    POSITIVE LOGITS
     Ratio
    0.80
    巴士
    0.77
    栥
    0.77
    خانه
    0.74
    يم
    0.74
     Ин
    0.72
    عه
    0.71
    بان
    0.71
    gunaan
    0.69
    ﺏ
    0.69
    Activations Density 0.003%

    No Known Activations