© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9774
    Prev
    Next
    INDEX
    Explanations

    Prophet forecasting

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

    This neuron activates on numeric tokens and number‐like identifiers (e.g. multi-digit counts, years, measurements).

    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
     입니다
    0.89
    ։
    0.87
    ⅾ
    0.83
    ।
    0.82
     käyttää
    0.82
    respuesta
    0.80
    ע
    0.80
    Ꮄ
    0.79
     नियु
    0.78
    "]').
    0.77
    POSITIVE LOGITS
     artefacts
    0.79
     Hanover
    0.78
     Wang
    0.77
     embry
    0.75
     Oops
    0.75
     Heroes
    0.73
     Appliances
    0.73
     Mise
    0.73
     freshest
    0.73
     endogenous
    0.73
    Activations Density 0.000%

    No Known Activations