© 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. 59253
    Prev
    Next
    INDEX
    Explanations

    period

    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
     monedas
    -1.63
     nothingness
    -1.57
     cómo
    -1.53
    ᐕ
    -1.48
     деца
    -1.48
     ТАК
    -1.47
     joyas
    -1.46
     listo
    -1.46
    ಿ
    -1.46
    ཫ
    -1.41
    POSITIVE LOGITS
    an
    1.77
     articoli
    1.66
    ,”
    1.64
     -
    1.59
    ,
    1.55
     is
    1.48
    ет
    1.44
     a
    1.44
     strumenti
    1.43
    ют
    1.42
    Activations Density 4.551%

    No Known Activations