© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128106
    Prev
    Next
    INDEX
    Explanations

    convolution, pixel, or data sampling parameters

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

    The neuron fires on numeric tokens representing floating‐point values (numbers with decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    f
    -1.87
    幛
    -1.85
    g
    -1.85
    se
    -1.83
    ro
    -1.83
    v
    -1.81
    стреча
    -1.80
    and
    -1.79
    de
    -1.76
    r
    -1.74
    POSITIVE LOGITS
    ellidos
    2.08
    these
    1.99
    灩
    1.96
    啖
    1.91
    麒麟
    1.76
     These
    1.74
    後記
    1.70
    𓋼
    1.66
    푣
    1.66
    setCellStyle
    1.66
    Activations Density 0.001%

    No Known Activations