© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    give when sending

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

    The neuron fires on decimal‐formatted numeric values (floating‐point 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
    grupo
    0.89
    ر
    0.88
     pergunta
    0.85
    ަރ
    0.85
    produto
    0.84
    direito
    0.84
     incrível
    0.84
    र
    0.83
    cadastro
    0.81
     سنا
    0.80
    POSITIVE LOGITS
     M
    0.84
     lessee
    0.72
     irregularities
    0.70
     l
    0.66
     promoted
    0.66
     ম
    0.65
     ordinate
    0.65
     Celebration
    0.64
     ordnance
    0.64
     Tourism
    0.64
    Activations Density 0.000%

    No Known Activations