© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    various programming and technical terms

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

    The neuron detects floating‐point numeric values (decimal measurements or specification 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
    an
    0.82
    SScript
    0.73
    泼
    0.71
    ルの
    0.71
    duğ
    0.70
    )}}{\
    0.70
    næ
    0.70
    setConfig
    0.69
    au
    0.69
     Singing
    0.68
    POSITIVE LOGITS
    स
    0.88
     immisc
    0.82
     fractures
    0.81
    чни
    0.79
    про
    0.79
    ک
    0.78
    ਸ
    0.78
    品牌
    0.77
    र्जर
    0.77
     브랜드
    0.76
    Activations Density 0.000%

    No Known Activations