© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    New Rules, Q, Mr

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

    This neuron detects numeric quantities (digits and measurements).

    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
     бампер
    -1.14
    ̿
    -1.13
     заменить
    -1.11
    eraard
    -1.09
    möbel
    -1.07
    opathie
    -1.06
     poate
    -1.05
    ὠ
    -1.05
    Efter
    -1.05
    Technically
    -1.05
    POSITIVE LOGITS
     [
    1.80
     without
    1.47
     together
    1.12
     from
    1.12
     they
    1.07
    []){
    1.07
     према
    1.05
    /.../
    1.02
    [
    1.00
    [+]
    0.98
    Activations Density 0.012%

    No Known Activations