© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8621
    Prev
    Next
    INDEX
    Explanations

    `Feature` delimiters or labels

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

    This neuron activates on numeric tokens—especially multi‐digit numbers and decimal values.

    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_31_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
     either
    0.54
    த்தின
    0.54
     X
    0.53
     pipeline
    0.51
    }_\
    0.51
     ích
    0.51
     intrav
    0.50
    }_{\
    0.50
     “
    0.49
     ঘটনার
    0.49
    POSITIVE LOGITS
    nBitCount
    0.59
     wechsel
    0.55
    mone
    0.55
     oynuyoruz
    0.55
    फ्ल
    0.54
    ครอบ
    0.54
    幟
    0.53
    เปลี่ยน
    0.53
     ಸಾಕಷ್ಟು
    0.52
    Cob
    0.52
    Activations Density 0.003%

    No Known Activations