© 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. 63666
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical ratios

    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
     Varela
    -0.74
    chanan
    -0.71
    luigi
    -0.68
    ISD
    -0.68
     kekuatan
    -0.64
     Anda
    -0.64
     þe
    -0.62
    ė
    -0.61
    Ꭷ
    -0.61
    Toole
    -0.60
    POSITIVE LOGITS
     ratio
    4.91
     Ratio
    4.59
    Ratio
    4.34
    ratio
    4.31
     ratios
    3.98
    RATIO
    3.44
     RATIO
    3.39
     Ratios
    3.30
    ratios
    3.13
     ration
    2.33
    Activations Density 0.082%

    No Known Activations