© 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. 67923
    Prev
    Next
    INDEX
    Explanations

    n followed by numbers or equals signs

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

    The neuron fires on mentions of sample‐size or count annotations of the form “n = <number>.”

    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
    </strong>
    -3.20
    gambarkan
    -3.11
    螄
    -3.03
    y
    -2.92
    鹮
    -2.86
    Ꮞ
    -2.66
     problemer
    -2.61
    ㈬
    -2.56
    𝕱
    -2.56
    ỽ
    -2.55
    POSITIVE LOGITS
    '
    4.41
    "
    3.69
     "
    3.38
    /
    3.27
     i
    2.80
     &
    2.75
    +
    2.73
    \
    2.63
     wahre
    2.58
     breite
    2.52
    Activations Density 0.045%

    No Known Activations