© 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. 112747
    Prev
    Next
    INDEX
    Explanations

    stresses or emphasizes

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

    This neuron detects occurrences of the “emphas-” root (e.g. emphasize, emphasised, emphasizing, emphasis).

    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
     a
    -1.72
     tegens
    -1.44
    lations
    -1.42
    mallows
    -1.36
     ещё
    -1.36
     waard
    -1.34
     utilizados
    -1.33
     nguyen
    -1.33
    #*
    -1.32
    lierung
    -1.32
    POSITIVE LOGITS
    </h4>
    1.54
    </h2>
    1.52
    after
    1.52
    Presentación
    1.48
    ：……
    1.42
    henswürdigkeiten
    1.41
    只是
    1.39
    レクション
    1.34
    iziert
    1.33
     багато
    1.33
    Activations Density 0.025%

    No Known Activations