© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33991
    Prev
    Next
    INDEX
    Explanations

    data structures

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

    The main thing this neuron does is detect numeric tokens (any standalone numbers or numeric values).

    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
    образие
    -0.94
    Fakta
    -0.93
    Последние
    -0.90
    usions
    -0.88
    tangentMode
    -0.87
    Zdrav
    -0.85
     tertarik
    -0.84
    enance
    -0.84
     药
    -0.84
     ultimi
    -0.83
    POSITIVE LOGITS
     their
    1.29
     of
    1.10
    对应的
    0.96
     the
    0.86
     Obec
    0.85
     both
    0.85
     Maybe
    0.84
     weaken
    0.82
     Гото
    0.81
     okrę
    0.81
    Activations Density 0.001%

    No Known Activations