© 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. 100533
    Prev
    Next
    INDEX
    Explanations

    how something is done

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

    The neuron activates on decimal numbers (tokens representing numbers with a decimal point).

    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
    </h2>
    -1.76
     uniquement
    -1.61
     incroyable
    -1.53
    '
    -1.47
     bricola
    -1.45
     dentelle
    -1.44
     olej
    -1.42
    </b>
    -1.42
    It
    -1.41
     traductions
    -1.39
    POSITIVE LOGITS
     this
    1.99
     those
    1.62
     such
    1.41
     when
    1.36
     and
    1.35
    CAREER
    1.31
     before
    1.30
     new
    1.22
     Kemudian
    1.21
     versus
    1.20
    Activations Density 0.069%

    No Known Activations