© 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. 39173
    Prev
    Next
    INDEX
    Explanations

    potential of or for

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

    This neuron activates on numeric expressions (numbers or measurements) in the text.

    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
    ?」
    -2.52
    灕
    -2.44
    !」
    -2.36
    ！」
    -2.25
    ίες
    -2.13
    谂
    -2.11
    爌
    -2.11
     médicaments
    -2.09
    哢
    -2.09
    騖
    -2.06
    POSITIVE LOGITS
    </sup>
    2.55
    {
    2.25
    <em>
    2.22
    也只是
    2.22
    也只能
    2.20
     
    1.98
     become
    1.96
     y
    1.87
    </b>
    1.87
    )
    1.77
    Activations Density 0.018%

    No Known Activations