© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80988
    Prev
    Next
    INDEX
    Explanations

    HTTP URLs, licence, and developers

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

    The neuron is specialized in detecting number tokens—i.e. sequences of digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    parm
    -0.82
    थ
    -0.74
    lea
    -0.72
    sgn
    -0.69
     море
    -0.68
    arbox
    -0.68
    Rollback
    -0.67
     MyApp
    -0.66
    ัน
    -0.66
    Parameteri
    -0.64
    POSITIVE LOGITS
     confirmé
    0.75
    ערב
    0.74
    jonas
    0.71
    ☓
    0.69
     liking
    0.69
    Cm
    0.68
     yılında
    0.67
    Libros
    0.67
    Créditos
    0.67
    icating
    0.67
    Activations Density 0.058%

    No Known Activations