© 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. 70806
    Prev
    Next
    INDEX
    Explanations

    lidocaine infusion or through encapsulation

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

    scientific or technical terms and chemical names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags unusually long, multi-syllable single tokens (e.g. technical or proper-name words).

    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
    舠
    -1.45
     vun
    -1.40
     succede
    -1.38
    дово
    -1.38
     incontra
    -1.31
     decisión
    -1.30
    wixt
    -1.30
     në
    -1.30
     velha
    -1.29
     notion
    -1.27
    POSITIVE LOGITS
     or
    1.67
    我们是
    1.47
     ВЫ
    1.45
     if
    1.43
     listos
    1.41
    していると
    1.38
    even
    1.37
     involucrados
    1.37
    鏖
    1.30
    Through
    1.30
    Activations Density 0.072%

    No Known Activations