© 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. 113188
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by descriptive item

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

    The neuron activates strongly on numeric expressions—especially floating‐point numbers (decimal values) and other quantitative data.

    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
     Instantly
    -1.45
    ◞
    -1.44
     peculiarly
    -1.41
    verns
    -1.36
     announces
    -1.34
     samsung
    -1.34
     sò
    -1.31
    </h3>
    -1.30
    又要
    -1.29
     GARANT
    -1.29
    POSITIVE LOGITS
    As
    1.51
    For
    1.36
    makedirs
    1.35
     by
    1.29
    Although
    1.28
    Not
    1.27
    我們
    1.27
     antworte
    1.26
     kurie
    1.25
    </em>
    1.23
    Activations Density 0.023%

    No Known Activations