© 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. 11166
    Prev
    Next
    INDEX
    Explanations

    st. louis

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

    The neuron strongly activates on numeric tokens in phone‐number–like sequences, i.e. it detects bits of phone numbers.

    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
    <0xA0>
    0.50
    если
    0.48
     एच
    0.46
    ový
    0.45
    ÿ
    0.45
     ۲
    0.44
    only
    0.44
     દ્વારા
    0.43
     американский
    0.43
    كامل
    0.43
    POSITIVE LOGITS
     beraten
    0.52
     え
    0.47
     amph
    0.46
    なら
    0.44
     abl
    0.43
     Urinary
    0.42
     quenching
    0.42
    거든
    0.42
     inquis
    0.42
     丶
    0.41
    Activations Density 0.002%

    No Known Activations