© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34843
    Prev
    Next
    INDEX
    Explanations

    holding a position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    getShared
    -0.85
    вий
    -0.73
     amplit
    -0.72
     kontaktieren
    -0.69
     produces
    -0.68
     گرد
    -0.68
    jaro
    -0.67
    伉
    -0.67
    خيص
    -0.67
     Gastgeber
    -0.65
    POSITIVE LOGITS
     holding
    3.63
     hold
    3.30
     held
    3.05
    holding
    2.97
    Holding
    2.88
    hold
    2.73
     occupy
    2.73
     holds
    2.72
     HOLD
    2.72
     occupying
    2.69
    Activations Density 0.091%

    No Known Activations