© 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. 245
    Prev
    Next
    INDEX
    Explanations

    final answer

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

    The neuron flags HTML‐style entity tokens (e.g. ampersands and the following entity names like “apos”) that appear in markup or escaped text.

    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
     samtidig
    0.23
     dość
    0.22
     goodwill
    0.21
     »
    0.21
    views
    0.21
    👇
    0.20
    hearted
    0.20
     conscientious
    0.20
    FBSDKAppEvents
    0.20
     mercantile
    0.20
    POSITIVE LOGITS
     ⿱
    0.22
    inositol
    0.21
     Expt
    0.21
     $_{\
    0.21
     Ха
    0.21
    OLYBD
    0.20
     Су
    0.20
     बहुपद
    0.20
     وبالتالي
    0.20
     T
    0.20
    Activations Density 2.552%

    No Known Activations