© 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. 345
    Prev
    Next
    INDEX
    Explanations

    import statements from

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

    This neuron detects numeric literal tokens in code (i.e., 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
     from
    -1.47
     each
    -1.42
     only
    -1.20
     for
    -1.15
     createSprite
    -1.13
    writeByte
    -1.12
     any
    -1.11
    そして
    -1.09
    onChangeText
    -1.08
     by
    -1.07
    POSITIVE LOGITS
     pretože
    1.20
    wonderful
    1.19
    取决
    1.18
    マジで
    1.18
    excellents
    1.17
    properly
    1.15
    extrême
    1.15
     shimmering
    1.15
    gruppen
    1.15
    zaamheid
    1.14
    Activations Density 0.004%

    No Known Activations