© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104223
    Prev
    Next
    INDEX
    Explanations

    code and technical specifications

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

    This neuron activates on code identifiers—especially longer variable, parameter, and class names (e.g. strategyOptions, MyClass, days).

    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
     when
    -1.41
     big
    -1.22
     has
    -1.16
     with
    -1.12
     It
    -1.09
     or
    -1.08
     so
    -1.06
    荭
    -1.06
    That
    -1.05
     atau
    -1.04
    POSITIVE LOGITS
    mbgg
    1.20
     espesor
    1.16
     combustível
    1.13
     horaire
    1.12
     encourag
    1.12
    לום
    1.10
     espanhol
    1.10
    thumbsup
    1.09
     unveils
    1.08
     cancelamento
    1.08
    Activations Density 0.051%

    No Known Activations