© 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. 22-GEMMASCOPE-RES-131K
    7. 26602
    Prev
    Next
    INDEX
    Explanations

    programming automation selectors

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

    The neuron strongly fires on code API identifiers related to selecting or finding elements (e.g. “By,” “findElement,” “Selector,” “find,” 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_22/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
     each
    -1.26
     prior
    -1.15
     verst
    -1.06
     completas
    -1.02
     except
    -0.96
    </i>
    -0.96
     generation
    -0.96
     espacial
    -0.95
    Df
    -0.95
    </h3>
    -0.95
    POSITIVE LOGITS
     viejas
    1.24
    ئي
    1.19
     olmad
    1.16
     sốt
    1.09
    Tutto
    1.09
    Faça
    1.09
     július
    1.07
    tamaan
    1.05
    Ecco
    1.04
    liğini
    1.04
    Activations Density 0.004%

    No Known Activations