© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45480
    Prev
    Next
    INDEX
    Explanations

    along with

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

    The neuron fires on numeric expressions—especially plain numbers and decimal measurements—in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     successivo
    -1.63
     following
    -1.63
     would
    -1.58
     by
    -1.55
     with
    -1.55
     and
    -1.52
     after
    -1.47
     svolta
    -1.43
     using
    -1.43
     having
    -1.42
    POSITIVE LOGITS
     綿
    1.43
     primaire
    1.42
    anzeigen
    1.39
     preciosa
    1.37
    kann
    1.37
    rollen
    1.36
    mittag
    1.36
     berätt
    1.34
    ANDRE
    1.30
    denn
    1.29
    Activations Density 0.029%

    No Known Activations