© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26956
    Prev
    Next
    INDEX
    Explanations

    mentioned aforementioned above

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

    The neuron fires on domain-specific technical or code-related object nouns (e.g. “button,” “API,” “calls,” “string,” “connection,” “opening”).

    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
     OnClickListener
    -1.01
     žena
    -0.98
     culturas
    -0.91
     Ursache
    -0.90
     estuvieron
    -0.90
     altı
    -0.90
     mejoras
    -0.88
     território
    -0.88
     instituciones
    -0.87
    さみ
    -0.87
    POSITIVE LOGITS
     mentioned
    1.73
     aforesaid
    1.56
     that
    1.48
     aforementioned
    1.35
    mentioned
    1.27
     mencionado
    1.20
     above
    1.12
     of
    1.09
    上述
    1.02
     mencion
    1.00
    Activations Density 0.088%

    No Known Activations