© 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. 34-GEMMASCOPE-RES-131K
    7. 117659
    Prev
    Next
    INDEX
    Explanations

    the subject/technique/concept

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

    The neuron detects numeric tokens (digits and numbers) in the 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
     presentará
    -1.03
    ăzi
    -1.03
     moeili
    -0.98
     rekomendasi
    -0.97
     urmă
    -0.96
     kombinasi
    -0.95
     reunió
    -0.94
     encontrarás
    -0.92
     desarrolló
    -0.91
     colgar
    -0.90
    POSITIVE LOGITS
     technique
    1.81
     phenomenon
    1.75
     concept
    1.44
     topic
    1.41
     modality
    1.31
     scheme
    1.30
    这项
    1.28
     same
    1.27
    该
    1.24
     genre
    1.23
    Activations Density 0.176%

    No Known Activations