© 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. 10-GEMMASCOPE-RES-131K
    7. 11452
    Prev
    Next
    INDEX
    Explanations

    foreign language indicators

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

    The neuron fires on standalone numeric tokens (sequences of digits), e.g. version or identifier 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_10/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
    signable
    -1.50
     ressemble
    -1.25
    bestos
    -1.25
    ͞
    -1.22
    pergillus
    -1.17
    ();)
    -1.17
     personagens
    -1.15
     максима
    -1.13
    otropy
    -1.13
    駅から
    -1.10
    POSITIVE LOGITS
     also
    1.48
     as
    1.47
     you
    1.38
    慮
    1.23
     seluruh
    1.19
    también
    1.19
     đính
    1.18
    från
    1.17
     ändert
    1.17
    饰演
    1.16
    Activations Density 0.234%

    No Known Activations