© 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. 14587
    Prev
    Next
    INDEX
    Explanations

    latex context `matrix` or `need`

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

    The neuron is activated by floating-point numeric tokens (i.e. decimal numbers, often image dimensions or measurement values).

    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
     médicament
    0.86
    药物
    0.82
    बाइक
    0.79
    씩
    0.79
     pazienti
    0.77
     insurrection
    0.77
     otherworldly
    0.76
    таж
    0.75
     fondamentali
    0.75
     mâles
    0.74
    POSITIVE LOGITS
    /-}$
    0.76
     пос
    0.71
     وي
    0.68
    kernels
    0.68
    ｄ
    0.68
     وس
    0.67
     الخارجية
    0.67
     تقل
    0.67
     ![
    0.66
     بمعنى
    0.66
    Activations Density 0.000%

    No Known Activations