© 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. 9261
    Prev
    Next
    INDEX
    Explanations

    numbers, money, and planning

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

    This neuron lights up on modal and future-oriented promotional language—especially phrases expressing ability or intent like “going to,” “can,” and “able 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
    D
    0.79
    Master
    0.77
    EVERY
    0.76
     (
    0.75
    Administ
    0.73
    GST
    0.73
    PR
    0.72
    （
    0.72
    ﾈ
    0.71
    EAST
    0.71
    POSITIVE LOGITS
     ähm
    1.04
     Lembrando
    1.01
     cuz
    1.00
     thio
    0.99
     quadrado
    0.98
     scrollBody
    0.96
     regresar
    0.95
     tengo
    0.95
     vezes
    0.92
     quero
    0.92
    Activations Density 0.007%

    No Known Activations