© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 208
    Prev
    Next
    INDEX
    Explanations

    to keep clear

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

    The neuron strongly activates on numeric tokens (quantities, measurements, or other numbers) in the text.

    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
    .
    0.39
    1
    0.36
     -
    0.34
     from
    0.34
     by
    0.34
    -
    0.34
    '
    0.34
    =
    0.34
     =
    0.33
    }
    0.33
    POSITIVE LOGITS
    ೃಷ್ಟ
    0.39
     tehdä
    0.36
     mitigate
    0.35
    Cadastro
    0.35
    Liens
    0.35
    Kết
    0.35
    ल्लिंग
    0.34
    Zespół
    0.34
    㡚
    0.33
     alleviate
    0.33
    Activations Density 1.731%

    No Known Activations