© 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. 2571
    Prev
    Next
    INDEX
    Explanations

    often

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

    The neuron is strongly triggered by em-dash punctuation (long dashes) in the 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
     👍
    0.91
    ленно
    0.74
    /)
    0.71
     satisfactory
    0.68
     😊
    0.68
    👍
    0.68
    rtle
    0.67
     🤗
    0.67
     😁
    0.66
    ;)
    0.65
    POSITIVE LOGITS
     нарушения
    0.76
     litig
    0.71
     dossiers
    0.71
     disinvestment
    0.71
     dracon
    0.70
     pokuš
    0.69
    ững
    0.69
     ambao
    0.68
     tinkering
    0.68
     litigants
    0.68
    Activations Density 0.161%

    No Known Activations