© 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. 85534
    Prev
    Next
    INDEX
    Explanations

    code examples or technical descriptions

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

    The neuron fires on isolated single‐character identifiers (e.g. g, P, t) in code.

    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
    経由
    -1.23
     forskellige
    -1.23
    にあります
    -1.12
     tía
    -1.09
    .
    -1.08
    ünkü
    -1.08
    <0x8E>
    -1.08
    を経
    -1.07
     lesquels
    -1.07
    ningen
    -1.07
    POSITIVE LOGITS
     would
    1.49
     on
    1.46
    on
    1.21
     reino
    1.17
     now
    1.15
    另一方面
    1.10
    的一些
    1.09
     egli
    1.08
     melaksanakan
    1.07
    gade
    1.06
    Activations Density 0.118%

    No Known Activations