© 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. 104280
    Prev
    Next
    INDEX
    Explanations

    both or either

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

    The neuron is specialized in detecting numeric tokens or numerical values (e.g. digits and numbers) 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
     views
    -0.81
     terkait
    -0.81
     entretenimiento
    -0.78
     svůj
    -0.77
     disegno
    -0.77
     TResult
    -0.76
    たちの
    -0.75
    丼
    -0.75
     shorter
    -0.75
    cursos
    -0.75
    POSITIVE LOGITS
    Both
    1.05
    Neither
    0.96
     Both
    0.93
    ทั้ง
    0.92
     begge
    0.90
    centric
    0.88
     Beide
    0.88
     neither
    0.87
     именно
    0.81
     только
    0.79
    Activations Density 0.033%

    No Known Activations