© 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. 34-GEMMASCOPE-RES-131K
    7. 63011
    Prev
    Next
    INDEX
    Explanations

    characteristics and extent

    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_34/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
     a
    -1.10
    ionados
    -1.02
    stä
    -1.02
    というわけで
    -0.98
     для
    -0.98
    Siapa
    -0.97
     برای
    -0.93
    ใน
    -0.93
    还有
    -0.91
    ález
    -0.90
    POSITIVE LOGITS
     that
    2.41
     which
    1.73
     consistent
    1.29
     iż
    1.19
     similar
    1.19
     conducive
    1.16
     previamente
    1.10
     other
    1.09
     που
    1.05
     they
    1.05
    Activations Density 0.103%

    No Known Activations