© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58177
    Prev
    Next
    INDEX
    Explanations

    last day or time

    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
    Negative Logits
    odeon
    -1.41
     your
    -1.26
    diteur
    -1.25
    函数
    -1.23
    鉨
    -1.21
     éxito
    -1.20
     traducciones
    -1.19
     くん
    -1.16
     pestañas
    -1.15
     社会
    -1.14
    POSITIVE LOGITS
    m
    1.18
    </h5>
    1.16
    和小
    1.13
    to
    1.09
     for
    1.05
    ne
    1.05
    ra
    1.05
    mesg
    1.02
    _{+
    1.02
    ations
    1.02
    Activations Density 0.043%

    No Known Activations