© 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. 3439
    Prev
    Next
    INDEX
    Explanations

    smart home features

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

    The neuron strongly responds to any token containing numerals, i.e. numbers or digits.

    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
    ে
    0.90
     precios
    0.79
     detainees
    0.78
     procured
    0.78
     enunciado
    0.78
     underpinned
    0.78
    鸣
    0.77
    िता
    0.77
     detained
    0.77
     detain
    0.76
    POSITIVE LOGITS
    érêt
    0.75
    že
    0.74
     jsonObj
    0.72
    אה
    0.70
    תר
    0.69
    );*/
    0.68
    ),$
    0.68
    tracker
    0.67
    )">
    0.66
    """
    0.66
    Activations Density 0.000%

    No Known Activations