© 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. 22361
    Prev
    Next
    INDEX
    Explanations

    words in brackets or parentheses

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

    The neuron fires on text enclosed in square brackets.

    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
     new
    -1.16
     sogenannten
    -1.06
     time
    -1.02
     really
    -1.02
    estimm
    -1.01
     vermutlich
    -1.00
    क्र
    -1.00
     so
    -1.00
     in
    -1.00
     actually
    -0.97
    POSITIVE LOGITS
     agujeros
    1.17
     według
    1.12
     donnant
    1.10
    anci
    1.08
     oxígeno
    1.08
    ௫
    1.06
    स्तु
    1.06
     calefacción
    1.05
     domestiques
    1.05
     secado
    1.04
    Activations Density 0.061%

    No Known Activations