© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60639
    Prev
    Next
    INDEX
    Explanations

    inequalities involving greek letters and variables

    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_10/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
     redor
    -1.52
    Some
    -1.46
    鯡
    -1.45
    Ꭸ
    -1.45
     sebagainya
    -1.45
     שלנו
    -1.42
     europé
    -1.41
    榦
    -1.39
     dentes
    -1.39
    ܜ
    -1.37
    POSITIVE LOGITS
    ’
    1.76
    </i>
    1.55
     and
    1.52
     it
    1.50
    lrrrr
    1.49
    </h1>
    1.45
     et
    1.42
     flesta
    1.35
    </b>
    1.32
    ࿊
    1.32
    Activations Density 0.011%

    No Known Activations