© 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. 112962
    Prev
    Next
    INDEX
    Explanations

    of the noun

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

    The neuron fires on numeric measurement values (especially decimal numbers) in scientific or technical contexts.

    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
     són
    -1.52
    ಿ
    -1.45
     maillot
    -1.45
    Ꮡ
    -1.41
     formid
    -1.40
    ments
    -1.38
     règne
    -1.37
     impecable
    -1.37
     reclu
    -1.36
     legendar
    -1.35
    POSITIVE LOGITS
     новая
    1.63
    );
    1.54
     like
    1.54
    );
    1.52
     такая
    1.37
    ATIVA
    1.36
    numsp
    1.35
     number
    1.34
     especially
    1.34
     line
    1.32
    Activations Density 0.181%

    No Known Activations