© 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. 16193
    Prev
    Next
    INDEX
    Explanations

    kind of

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

    The neuron strongly responds to numeric tokens—especially section or version numbers and other digit-based identifiers.

    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
    includes
    0.67
    times
    0.64
    மான
    0.64
    a
    0.63
      
    0.63
    shared
    0.60
    copied
    0.60
    o
    0.60
    CLUDES
    0.59
    8
    0.58
    POSITIVE LOGITS
     basilaires
    0.64
     equally
    0.60
     proprement
    0.59
     kV
    0.59
     etiology
    0.58
     pathophysiology
    0.58
     மற்ற
    0.58
    វិញ
    0.58
     본격
    0.57
    博物館
    0.57
    Activations Density 0.224%

    No Known Activations