© 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. 2924
    Prev
    Next
    INDEX
    Explanations

    due diligence assessment

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

    The neuron is strongly activated by numeric tokens (numbers, digits, dates, measurements, etc.).

    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
     같
    0.77
    ↵↵
    0.64
     role
    0.62
    0
    0.61
     []:
    0.59
     Reebok
    0.58
     Reuters
    0.58
     Brewer
    0.57
    ב
    0.56
    ...",
    0.56
    POSITIVE LOGITS
     monomials
    0.86
    Fragments
    0.84
    䛶
    0.82
    ங்க்
    0.82
    㖮
    0.81
    ingan
    0.81
    ontal
    0.80
    InData
    0.80
     тысячи
    0.80
    idded
    0.80
    Activations Density 0.000%

    No Known Activations