© 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. 10-GEMMASCOPE-RES-131K
    7. 7507
    Prev
    Next
    INDEX
    Explanations

    potential, trend, reason

    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
     diseñar
    -1.47
     czuj
    -1.41
    how
    -1.33
     komende
    -1.32
    you
    -1.30
     wersji
    -1.29
     moż
    -1.28
     głó
    -1.27
     beeind
    -1.27
     кто
    -1.27
    POSITIVE LOGITS
     naturali
    1.34
     formato
    1.31
    >−</
    1.20
     eigene
    1.19
    <bos>
    1.16
     ellas
    1.16
     lifeless
    1.16
    岁月
    1.15
     ihrer
    1.13
    ,“
    1.13
    Activations Density 0.003%

    No Known Activations