© 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. 93143
    Prev
    Next
    INDEX
    Explanations

    periods, moments, or intervals

    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
    ած
    -0.85
    phytes
    -0.81
     memes
    -0.81
     problemas
    -0.80
     corporativa
    -0.79
    iza
    -0.77
     already
    -0.77
     ролях
    -0.77
    ้อน
    -0.76
    enta
    -0.75
    POSITIVE LOGITS
     periods
    4.31
    periods
    3.00
     moments
    2.91
     Periods
    2.86
     перио
    2.55
    Periods
    2.50
     períodos
    2.38
     intervals
    2.27
     périodes
    2.25
    moments
    2.23
    Activations Density 0.091%

    No Known Activations