© 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. 22-GEMMASCOPE-RES-131K
    7. 72827
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions

    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_22/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
     what
    -1.91
     can
    -1.45
     it
    -1.45
     might
    -1.31
     should
    -1.31
     could
    -1.29
     really
    -1.26
     now
    -1.25
     his
    -1.24
     quickly
    -1.23
    POSITIVE LOGITS
     majority
    1.66
     большинстве
    1.63
     большин
    1.62
    Majority
    1.62
     большинство
    1.57
    majority
    1.48
     полови
    1.45
     percentage
    1.41
    Percentage
    1.36
     percent
    1.34
    Activations Density 0.091%

    No Known Activations