© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111479
    Prev
    Next
    INDEX
    Explanations

    stdio, urlencoded, Michael, Popular, Plan

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

    The neuron fires strongly on tokens related to I/O and form‐encoding—most notably “stdio” (and its variants) and “x-www-form-urlencoded.”

    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
    ↵
    -2.06
     said
    -2.03
     where
    -2.02
    1
    -1.99
     not
    -1.94
    知道
    -1.94
     touted
    -1.91
     still
    -1.82
     However
    -1.82
     been
    -1.78
    POSITIVE LOGITS
    糴
    2.45
    珢
    2.33
    牂
    2.30
    ⸢
    2.30
    providedIn
    2.30
    ⬈
    2.25
    踯
    2.22
     hırka
    2.20
    籴
    2.19
    蹀
    2.17
    Activations Density 0.000%

    No Known Activations