© 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. 31366
    Prev
    Next
    INDEX
    Explanations

    proportion or accordance

    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
    zawa
    -0.74
    ╴
    -0.69
    ριά
    -0.69
     área
    -0.68
    scrollTop
    -0.68
    illips
    -0.68
     Bathurst
    -0.66
    Pé
    -0.66
     xếp
    -0.66
    賃
    -0.65
    POSITIVE LOGITS
     proportion
    5.63
    proportion
    5.31
     proportions
    5.28
     Proportion
    4.88
    propor
    4.81
    Proportion
    4.81
     пропор
    4.66
     Propor
    4.56
     propor
    4.28
     proportional
    4.28
    Activations Density 0.061%

    No Known Activations