© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    of X

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

    This neuron spotlights section headers or titles formed by a key noun followed by a preposition (e.g. “Panel of,” “Overview of,” “Gateway Interface to”).

    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
    uten
    0.66
    。
    0.61
    '.
    0.60
    ,
    0.60
    ।
    0.59
    hed
    0.57
     habil
    0.57
    e
    0.57
    bo
    0.55
    ↵
    0.55
    POSITIVE LOGITS
     laterales
    0.68
     구입
    0.68
     Autres
    0.66
     Considerable
    0.65
    Aq
    0.64
     основных
    0.62
    ıları
    0.61
    ómago
    0.60
     Umum
    0.60
     الوط
    0.59
    Activations Density 0.193%

    No Known Activations