© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77864
    Prev
    Next
    INDEX
    Explanations

    educational standards

    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
     CiNii
    -0.86
     northbound
    -0.77
    lové
    -0.75
     Scully
    -0.74
     Dunne
    -0.74
     Seminars
    -0.73
    jning
    -0.73
     succumbed
    -0.73
     JIT
    -0.73
     очи
    -0.71
    POSITIVE LOGITS
     standards
    2.92
     Standards
    2.55
    Standards
    2.39
    standards
    2.20
     STANDARDS
    1.99
     стандар
    1.73
     estándares
    1.41
     standard
    1.27
     Standard
    1.24
     Common
    1.23
    Activations Density 0.028%

    No Known Activations