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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129976
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    will be followed by a state

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cannot
    -1.53
    gelijke
    -1.51
    traueranzeige
    -1.48
    ௡
    -1.47
     theres
    -1.46
    wia
    -1.45
    ꯳
    -1.44
    溼
    -1.43
    ㌘
    -1.43
     existem
    -1.42
    POSITIVE LOGITS
     be
    2.27
     soon
    1.55
    I
    1.51
     able
    1.48
     galima
    1.41
     "
    1.38
    {
    1.38
     sosok
    1.36
    hopefully
    1.29
    get
    1.26
    Activations Density 0.044%

    No Known Activations