© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65207
    Prev
    Next
    INDEX
    Explanations

    Computer Sciences, CES, University departments

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

    The neuron flags mentions of academic disciplines, departments, or college names (e.g. “College of Arts and Sciences,” “Electrical and Computer Engineering”).

    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
     it
    -1.63
    ");
    -1.51
     is
    -1.46
    '];
    -1.43
    </h2>
    -1.43
     ALL
    -1.42
     their
    -1.34
     represents
    -1.31
     uses
    -1.30
    ()");
    -1.30
    POSITIVE LOGITS
     grève
    1.40
     plongée
    1.34
     conséquence
    1.27
     prípade
    1.27
     predetermin
    1.20
     perceber
    1.20
    oggi
    1.19
     ボール
    1.19
     Référence
    1.18
     Répondre
    1.17
    Activations Density 0.026%

    No Known Activations