© 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. 34-GEMMASCOPE-RES-131K
    4. 118416
    Prev
    Next
    INDEX
    Explanations

    surveys and reports

    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
     okol
    -0.82
     emple
    -0.68
     dismin
    -0.67
    Bim
    -0.67
     skóra
    -0.66
    тью
    -0.66
     libremente
    -0.66
    負け
    -0.66
     gravidez
    -0.66
    mAdapter
    -0.65
    POSITIVE LOGITS
     questionnaire
    1.09
     sample
    0.97
     questionnaires
    0.95
     quarterly
    0.95
     Quarterly
    0.92
     Questionnaire
    0.91
     monthly
    0.90
    ampling
    0.89
    survey
    0.88
     Concepts
    0.88
    Activations Density 0.039%

    No Known Activations