© 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. 91052
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

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

    This neuron fires on numeric constants (multi‐digit numbers) 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_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
    暂时
    -0.87
     tears
    -0.84
     hver
    -0.83
    _()
    -0.74
    ännande
    -0.73
    のお
    -0.73
     varje
    -0.72
     baig
    -0.72
     larmes
    -0.72
    /***/
    -0.70
    POSITIVE LOGITS
    친
    0.69
     sherpa
    0.66
    nbr
    0.64
     Tij
    0.64
    센
    0.63
    🎎
    0.63
     commuting
    0.63
    🛵
    0.62
     управління
    0.62
     追
    0.62
    Activations Density 0.027%

    No Known Activations