© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    used to introduce explanations

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

    The neuron flags tokens that occur around explicit numeric or quantitative information, i.e. words adjacent to measurements, counts, or other 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
     scris
    0.76
    訴
    0.73
     diatas
    0.73
     escrever
    0.72
     Bewert
    0.72
    addKill
    0.71
     mariage
    0.71
    ཥ
    0.70
    写
    0.70
     scrive
    0.70
    POSITIVE LOGITS
     воспользоваться
    0.76
     anticipate
    0.75
     anticipated
    0.71
     NOAA
    0.68
     hopeful
    0.67
     anticipating
    0.66
     momentarily
    0.66
     inclement
    0.66
     awaiting
    0.66
     promptly
    0.64
    Activations Density 0.149%

    No Known Activations