© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5889
    Prev
    Next
    INDEX
    Explanations

    power rule

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

    The neuron fires on isolated numeric tokens (especially standalone numbers and decimals) rather than on regular 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
     of
    0.76
    ;
    0.74
    c
    0.72
    :
    0.72
    ,
    0.68
    d
    0.66
    .
    0.64
      
    0.63
    huge
    0.62
    work
    0.62
    POSITIVE LOGITS
     sadistic
    0.94
     میکرز
    0.84
     Zusätzlich
    0.84
     кноп
    0.83
    étion
    0.82
     Wikiseite
    0.80
     Hanya
    0.79
    руются
    0.79
    ྥ
    0.78
     Более
    0.78
    Activations Density 0.001%

    No Known Activations