© 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. 68593
    Prev
    Next
    INDEX
    Explanations

    layout sizing and spacing

    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
     olabilir
    -1.46
     artık
    -1.37
     possible
    -1.35
     about
    -1.34
     or
    -1.33
     consequences
    -1.31
     improved
    -1.30
     posiblemente
    -1.26
     likely
    -1.25
    BIÉN
    -1.22
    POSITIVE LOGITS
    }),
    1.48
     your
    1.41
     sommar
    1.38
     conférence
    1.37
    TokenNameDOT
    1.30
    ↠
    1.30
    rsquo
    1.29
     caisse
    1.27
    сени
    1.23
     quarto
    1.22
    Activations Density 0.153%

    No Known Activations