© 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. 16025
    Prev
    Next
    INDEX
    Explanations

    describing things

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

    The neuron spikes on decimal-formatted numbers (floating-point numeric tokens).

    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
     ancients
    0.71
    lof
    0.68
    .
    0.66
     man
    0.63
     inscription
    0.62
    ini
    0.61
    ലി
    0.61
     incid
    0.61
    வரி
    0.61
    ues
    0.60
    POSITIVE LOGITS
     strikingly
    0.78
     Owing
    0.77
     parceria
    0.77
    啝
    0.77
    आर
    0.76
    ━━━━━━━━
    0.75
    बॉलीवुड
    0.73
     teilweise
    0.73
    TorpedoStore
    0.73
     pistachio
    0.72
    Activations Density 0.001%

    No Known Activations