© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    as determined by

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

    The neuron fires on numeric measurement contexts—phrases where a value is given along with “measured by,” “determined by,” or “as” in scientific reporting.

    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
    StoryboardSegue
    -1.86
     is
    -1.63
     craindre
    -1.56
     was
    -1.52
    </strong>
    -1.50
     tormenta
    -1.50
    关于
    -1.49
    </sup>
    -1.48
     bagaimana
    -1.40
     perfe
    -1.38
    POSITIVE LOGITS
     by
    1.92
     on
    1.73
     their
    1.72
     the
    1.69
     according
    1.60
    on
    1.40
     respective
    1.38
     otorg
    1.36
    in
    1.35
     both
    1.29
    Activations Density 0.108%

    No Known Activations