© 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. 16371
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

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

    The neuron fires on numeric literals (integer or floating‐point constants) 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_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
     вашем
    -1.23
     Envío
    -1.22
     paramètres
    -1.20
     Municipalidad
    -1.18
     Políticas
    -1.18
     новый
    -1.18
     Capacidad
    -1.17
     Février
    -1.17
     mojej
    -1.13
     Producción
    -1.13
    POSITIVE LOGITS
     and
    1.81
     which
    1.44
     these
    1.26
     often
    1.20
    dulos
    1.10
     Currently
    1.06
     will
    1.03
     other
    1.02
     commonly
    1.02
     have
    1.01
    Activations Density 0.002%

    No Known Activations