© 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. 72124
    Prev
    Next
    INDEX
    Explanations

    describing role or properties

    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
     to
    -1.78
     at
    -1.44
     from
    -1.34
     across
    -1.32
     both
    -1.32
     publicados
    -1.32
    をしていた
    -1.31
    pillow
    -1.30
     aprendiz
    -1.30
    chés
    -1.30
    POSITIVE LOGITS
    O
    1.34
    łgorzata
    1.30
     vissa
    1.30
    8
    1.23
     कुछ
    1.20
     isso
    1.20
     certaine
    1.18
    ковым
    1.16
     SOME
    1.16
     कि
    1.16
    Activations Density 0.290%

    No Known Activations