© 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. 22-GEMMASCOPE-RES-131K
    7. 15592
    Prev
    Next
    INDEX
    Explanations

    Contact Information or Q:

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

    The neuron responds to occurrences of the string "path" when defining an SVG <path> element (e.g. in React.createElement('path', …)).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    沙发
    -1.27
    そして
    -1.14
    そういえば
    -1.11
    珧
    -1.11
    ハンドメイド
    -1.10
     guapo
    -1.09
     harde
    -1.09
    Этот
    -1.09
    お店の
    -1.09
     Toute
    -1.08
    POSITIVE LOGITS
     \%$,
    1.35
    </i>
    1.26
    </strong>
    1.21
     like
    1.19
     unserer
    1.10
     öst
    1.06
     by
    1.05
    命的
    1.04
    lindung
    1.04
    kerja
    1.04
    Activations Density 0.000%

    No Known Activations