© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3359
    Prev
    Next
    INDEX
    Explanations

    try block start

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

    The neuron strongly activates on tokens that are numeric (e.g. digits, ISBNs, measurements, IDs)—in other words, it detects numbers and numeric sequences.

    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
     ר
    0.66
     waterfowl
    0.66
    ১৫
    0.65
     outra
    0.65
     휴
    0.64
    <unused0>
    0.64
     padam
    0.64
    
    0.64
     เซ
    0.63
    业协会
    0.63
    POSITIVE LOGITS
    ے
    0.64
    同様
    0.61
    Similarly
    0.60
    ेंट
    0.59
    Likewise
    0.59
    <0x8A>
    0.58
    Were
    0.57
    ாட்டு
    0.57
     Autobi
    0.57
    च्
    0.56
    Activations Density 0.000%

    No Known Activations