© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130369
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric literals (multi‐digit number tokens) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     vermelhas
    -1.33
    deviantart
    -1.32
    ceptable
    -1.22
    angkap
    -1.20
    :"#
    -1.20
    lıyor
    -1.16
    <mask>
    -1.15
    ächt
    -1.14
     pitié
    -1.14
    |','
    -1.13
    POSITIVE LOGITS
    ceous
    1.29
    などを
    1.28
    med
    1.20
    he
    1.20
    </em>
    1.19
    ariConfig
    1.17
    此外
    1.17
     lastly
    1.16
    などが
    1.16
     ect
    1.15
    Activations Density 0.010%

    No Known Activations