© 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. 22-GEMMASCOPE-RES-131K
    7. 65963
    Prev
    Next
    INDEX
    Explanations

    p-values and statistical significance

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

    The neuron is specialized to spot numerical statistical values (e.g. p-values) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     abſ
    -1.52
    siamo
    -1.37
     soyez
    -1.35
     descubre
    -1.32
     欣赏
    -1.29
     tragé
    -1.27
    ଼
    -1.27
    ऎ
    -1.27
     anuncia
    -1.27
     pouvez
    -1.26
    POSITIVE LOGITS
    5
    1.36
    2
    1.34
    0
    1.32
    <bos>
    1.31
    3
    1.28
    7
    1.27
    4
    1.23
    8
    1.19
     عدة
    1.15
    M
    1.15
    Activations Density 0.005%

    No Known Activations