© 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. 10-GEMMASCOPE-RES-131K
    7. 60216
    Prev
    Next
    INDEX
    Explanations

    states facts or information

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

    The neuron flags formal litigation/discourse markers and reporting verbs in legal documents (e.g. “stating,” “shown,” “evidence,” “case”).

    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
    </b>
    -1.91
     biß
    -1.62
    $
    -1.53
     mêmes
    -1.48
    <i>
    -1.42
    ２
    -1.39
    OSPITAL
    -1.39
     posiciones
    -1.35
     progressivement
    -1.35
     humeur
    -1.34
    POSITIVE LOGITS
    </h3>
    2.13
     in
    1.61
     because
    1.56
     if
    1.53
     about
    1.42
     until
    1.38
    Beschrijving
    1.34
    、“
    1.33
     intensive
    1.33
     have
    1.33
    Activations Density 0.037%

    No Known Activations