© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 290
    Prev
    Next
    INDEX
    Explanations

    import package android

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

    The neuron is triggered by sequences of digits, i.e. numeric tokens or literals in the 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
     maîtrise
    -1.05
     graden
    -0.92
    áky
    -0.91
    .*;
    -0.89
    ゴール
    -0.86
     organizes
    -0.86
     乳
    -0.85
     Bé
    -0.85
     estão
    -0.85
    prest
    -0.85
    POSITIVE LOGITS
     yine
    0.85
     Júnior
    0.83
     unsigned
    0.82
    Ŕ
    0.82
     edilen
    0.81
     wynosi
    0.80
     covid
    0.80
    arsh
    0.80
    BeforeMethod
    0.80
     impeach
    0.79
    Activations Density 0.002%

    No Known Activations