© 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. 34606
    Prev
    Next
    INDEX
    Explanations

    minimum TOEFL scores

    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
    Opti
    -0.77
    licence
    -0.73
     EDITORS
    -0.72
    贩
    -0.71
    opti
    -0.71
    VIV
    -0.71
     Mädchen
    -0.70
     learn
    -0.70
    资质
    -0.70
     udd
    -0.69
    POSITIVE LOGITS
     IELTS
    1.40
    烤
    0.88
     monoclonal
    0.85
    Describe
    0.83
    yuan
    0.82
    NPs
    0.82
    Ostat
    0.81
    あなたが
    0.80
    雅
    0.78
    diagram
    0.75
    Activations Density 0.002%

    No Known Activations