© 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. 14853
    Prev
    Next
    INDEX
    Explanations

    Whether / All / My / Skip / Youtube / Fast / There / The / Well

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

    The neuron detects standalone day‐of‐month numerals appearing in citation date strings.

    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
    -¡
    -1.64
     nombreux
    -1.55
    ptt
    -1.54
     souvent
    -1.47
    苤
    -1.46
     Redacción
    -1.45
     dénon
    -1.44
     Luego
    -1.43
    蟶
    -1.42
     mijn
    -1.41
    POSITIVE LOGITS
     этих
    2.13
    It
    2.00
     всех
    1.94
     on
    1.89
    These
    1.88
     these
    1.80
     and
    1.71
     at
    1.69
    t
    1.68
    縝
    1.68
    Activations Density 0.174%

    No Known Activations