© 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. 16054
    Prev
    Next
    INDEX
    Explanations

    android

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

    The neuron is primarily detecting numeric literals (i.e. tokens composed of digits) in code or markup.

    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
    taya
    -1.11
    leine
    -1.08
     září
    -1.02
    tutup
    -1.02
    Tecnologia
    -1.02
     superfí
    -1.02
    weiß
    -1.00
     longa
    -1.00
     dvě
    -1.00
    besondere
    -0.98
    POSITIVE LOGITS
    ?
    1.10
    я
    1.04
    b
    0.97
    —
    0.97
    -
    0.96
     مورد
    0.92
    I
    0.91
    ,
    0.90
    信息
    0.89
     we
    0.88
    Activations Density 0.008%

    No Known Activations