© 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. 22-GEMMASCOPE-RES-131K
    4. 84440
    Prev
    Next
    INDEX
    Explanations

    Corrosion and Search form

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

    The neuron detects numeric tokens (series 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_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
    jame
    -0.93
    statechange
    -0.91
     opinião
    -0.91
    skar
    -0.91
    Appellee
    -0.90
     mój
    -0.88
     mídia
    -0.88
    вне
    -0.88
     ilang
    -0.87
    damas
    -0.87
    POSITIVE LOGITS
     such
    1.05
    ()){
    1.04
     peuvent
    1.04
    ':{
    1.01
    ,'"
    0.99
     cyclisme
    0.98
    izophren
    0.96
    .\\
    0.94
     حم
    0.94
     nếu
    0.94
    Activations Density 0.001%

    No Known Activations