© 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. 128771
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals in code (multi‐digit number tokens).

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

    comparison operators

    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
    8
    -1.58
    を
    -1.52
    3
    -1.41
    が
    -1.38
    は
    -1.34
    7
    -1.32
    1
    -1.31
    6
    -1.30
    2
    -1.30
    5
    -1.30
    POSITIVE LOGITS
    んですよね
    1.33
     manualidades
    1.30
     fábricas
    1.25
     vêtement
    1.23
     muñecas
    1.20
     cepillo
    1.18
    に来
    1.15
     lámparas
    1.13
     verduras
    1.13
     bicicletas
    1.13
    Activations Density 0.009%

    No Known Activations