© 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. 9827
    Prev
    Next
    INDEX
    Explanations

    moving towards

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

    The neuron strongly activates on numeric and quantitative expressions (digits and words like “one”) indicating quantities or metadata.

    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
    وک
    0.86
    ট
    0.80
    स
    0.77
    ตลาด
    0.76
     dä
    0.75
    ในการ
    0.74
    Ὀ
    0.74
    ราช
    0.74
     соло
    0.74
    س
    0.74
    POSITIVE LOGITS
    ian
    0.92
    ianum
    0.83
    âm
    0.82
    ne
    0.80
    ism
    0.80
    ée
    0.80
    ll
    0.79
    th
    0.78
    erm
    0.77
    anged
    0.77
    Activations Density 0.000%

    No Known Activations