© 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. 8509
    Prev
    Next
    INDEX
    Explanations

    * Hilbert , times ;

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

    The neuron flags unusually rare or infrequent tokens (e.g. obscure names, codes, numeric identifiers, or uncommon proper nouns).

    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
    गुरु
    0.95
    加入了
    0.91
    ꩡ
    0.90
    dincer
    0.89
     pazienti
    0.88
    ০
    0.88
     racionais
    0.86
    홧
    0.86
     americanos
    0.86
     constantes
    0.85
    POSITIVE LOGITS
     Le
    0.74
     n
    0.72
     properties
    0.67
     le
    0.66
     ad
    0.65
     ode
    0.65
     argparse
    0.64
     off
    0.63
     offices
    0.62
     overs
    0.62
    Activations Density 0.001%

    No Known Activations