© 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. 68023
    Prev
    Next
    INDEX
    Explanations

    applying to rules or plugins

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

    The neuron strongly activates on occurrences of the token “apply” (as in function or method calls named apply).

    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
    H
    -2.69
    X
    -2.64
    </h1>
    -2.50
    C
    -2.45
    をも
    -2.45
     i
    -2.45
    ꔹ
    -2.41
    幼稚
    -2.38
     ‘
    -2.38
    на
    -2.38
    POSITIVE LOGITS
    焄
    3.25
    1
    3.05
    呖
    2.92
    ه
    2.88
    谖
    2.77
    摃
    2.75
    懨
    2.72
    韡
    2.72
     cristo
    2.69
    灃
    2.69
    Activations Density 0.026%

    No Known Activations