© 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. 34-GEMMASCOPE-RES-131K
    7. 92182
    Prev
    Next
    INDEX
    Explanations

    purchase and published terms

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

    The neuron strongly activates on numeric tokens (e.g. version numbers, counts, literal numbers).

    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
    telle
    -0.74
    Britain
    -0.73
     Complement
    -0.73
    چرخ
    -0.73
     homeward
    -0.73
    empla
    -0.71
    IZONA
    -0.71
    туга
    -0.70
    حياتها
    -0.69
    html
    -0.69
    POSITIVE LOGITS
     Pri
    0.68
    ありがたい
    0.66
    اعدة
    0.65
     hopping
    0.65
     pri
    0.64
     ungkapnya
    0.61
    ͪ
    0.59
     footprint
    0.59
     отметить
    0.58
     Desarrollo
    0.58
    Activations Density 0.070%

    No Known Activations