© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12824
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun introducer

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

    This neuron activates on numeric tokens representing decimal values (numbers with a fractional component).

    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
    鹀
    -1.98
     revela
    -1.94
    during
    -1.88
    despite
    -1.87
    蹿
    -1.82
     avocat
    -1.80
     célèbre
    -1.79
     cinq
    -1.79
    regarding
    -1.76
    そういえば
    -1.75
    POSITIVE LOGITS
     with
    2.41
     that
    2.25
     now
    2.22
     also
    2.08
     and
    2.08
     from
    2.06
     other
    2.00
    .......
    1.77
     liknande
    1.77
    كتشاف
    1.75
    Activations Density 0.512%

    No Known Activations