© 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. 69805
    Prev
    Next
    INDEX
    Explanations

    html meta charset

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

    The neuron fires primarily on occurrences of the “NotNull” annotation.

    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
    ↵↵
    -2.88
     "
    -2.47
    (
    -2.39
     leur
    -2.30
    は
    -2.20
    𐑂
    -2.17
    rophes
    -2.14
    素晴らしい
    -2.09
     nonstop
    -2.09
    ༎
    -2.03
    POSITIVE LOGITS
     Hinblick
    2.88
    the
    2.28
    狆
    2.27
    ྅
    2.22
    =“
    2.19
     recalling
    2.14
     unangemess
    2.09
     ホテル
    2.08
    翾
    2.05
     料金
    2.03
    Activations Density 0.005%

    No Known Activations