© 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. 11533
    Prev
    Next
    INDEX
    Explanations

    circular or during

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

    The neuron strongly activates on numeric tokens (including integers and especially decimal‐formatted numbers).

    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
    ChatGPT
    0.68
     нужны
    0.66
    꽤
    0.66
    けれど
    0.66
     complicated
    0.64
     সর্বনাশ
    0.64
    它的
    0.64
     তবু
    0.63
     ಸಂಧಿ
    0.63
    觊
    0.63
    POSITIVE LOGITS
     durant
    0.84
     במהלך
    0.80
     actividad
    0.78
     durante
    0.77
     خلال
    0.76
     এসময়
    0.76
     during
    0.75
     aktivnosti
    0.74
     presencia
    0.73
     dimana
    0.71
    Activations Density 0.027%

    No Known Activations