© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    generating text after prompts

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

    The neuron is highly sensitive to uppercase abbreviations or initial‐ism tokens (e.g. “U-2,” “U.S.”, etc.).

    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
    I
    0.75
    •
    0.70
    Open
    0.66
    let
    0.63
    Let
    0.62
    Space
    0.61
    Reader
    0.61
    fold
    0.61
    S
    0.61
    Dec
    0.60
    POSITIVE LOGITS
     putern
    0.62
     notizie
    0.57
     való
    0.57
     leggera
    0.57
     avances
    0.56
     densément
    0.55
     groep
    0.55
     τύ
    0.55
     aantal
    0.54
     regelmatig
    0.54
    Activations Density 0.057%

    No Known Activations