© 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. 113772
    Prev
    Next
    INDEX
    Explanations

    related to code components

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

    technical terms related to code optimization, performance, and side effects in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on high-level programming concept keywords—especially React/Redux API names and functional/side-effect terms such as “thunk,” “side effect,” “PureComponent,” “StatelessFunctionalComponent,” “memoize,” “Suspense,” “reuse,” etc.

    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
    </i>
    -1.34
     from
    -1.30
     both
    -1.16
     successfully
    -1.15
     if
    -1.15
     by
    -1.13
     “
    -1.13
     and
    -1.09
     has
    -1.08
     used
    -1.08
    POSITIVE LOGITS
     électron
    1.26
    ிக
    1.22
    了两
    1.21
    鲩
    1.19
    werten
    1.19
     κρα
    1.18
     berätt
    1.16
     quema
    1.16
    𝗥
    1.16
     vendidos
    1.15
    Activations Density 0.076%

    No Known Activations