© 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. 10-GEMMASCOPE-RES-131K
    7. 66860
    Prev
    Next
    INDEX
    Explanations

    screen resolution dimensions

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

    The neuron strongly activates on numeric tokens representing measurements or dimensions that include decimal points (e.g. “17.5”).

    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
     as
    -3.33
     because
    -2.94
     in
    -2.75
     if
    -2.72
     and
    -2.72
     from
    -2.66
     after
    -2.63
     to
    -2.55
     there
    -2.55
     is
    -2.53
    POSITIVE LOGITS
    Kondisi
    2.47
     magnifiques
    2.38
     relâche
    2.38
    킁
    2.33
    媃
    2.28
    媄
    2.25
     rafraî
    2.23
    〮
    2.23
    Sudah
    2.19
    Kegiatan
    2.19
    Activations Density 0.013%

    No Known Activations