© 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. 54208
    Prev
    Next
    INDEX
    Explanations

    JavaScript, jQuery, C++, Python, YAML, Objective-C

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

    The neuron is triggered by numeric literals (digits) in code or text.

    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
     pán
    -1.47
     vín
    -1.46
     花朵
    -1.45
     hés
    -1.41
     elétrico
    -1.41
    reibe
    -1.39
    えっ
    -1.38
    ごめん
    -1.36
     apporter
    -1.34
     菇
    -1.34
    POSITIVE LOGITS
     —
    1.35
     if
    1.29
     and
    1.28
     m
    1.27
     M
    1.24
     It
    1.23
     F
    1.21
     I
    1.20
     E
    1.19
     or
    1.18
    Activations Density 0.020%

    No Known Activations