© 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. 22-GEMMASCOPE-RES-131K
    7. 104639
    Prev
    Next
    INDEX
    Explanations

    true/false answers

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

    The neuron activates on numeric tokens—i.e. sequences of digits representing 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_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
     of
    -1.53
     作り方
    -1.27
    РЯ
    -1.24
     to
    -1.15
    Considering
    -1.07
    Apparently
    -1.06
     ledig
    -1.06
    bezpiecz
    -1.05
    できるので
    -1.05
     menik
    -1.05
    POSITIVE LOGITS
     yes
    1.30
     true
    1.26
     not
    1.14
    oczes
    1.14
     whether
    1.01
     what
    1.01
     prosegu
    1.00
    owieck
    0.96
     false
    0.95
     Yes
    0.94
    Activations Density 0.005%

    No Known Activations