© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    early 2024 SNAPSHOT

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

    The neuron is triggered by numeric tokens or digit sequences (e.g. numbers, measurements, phone‐number parts).

    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
    や
    0.48
    方針
    0.46
     کردن
    0.44
    وہ
    0.43
     だけ
    0.43
    Appuntamento
    0.43
     చర్య
    0.41
    جرة
    0.40
    딕
    0.40
    を行う
    0.40
    POSITIVE LOGITS
     October
    0.44
    0
    0.43
     January
    0.43
    7
    0.43
     bred
    0.43
     February
    0.42
     July
    0.42
     September
    0.42
     ৭৮
    0.42
     beautiful
    0.40
    Activations Density 1.476%

    No Known Activations