© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105081
    Prev
    Next
    INDEX
    Explanations

    other sites

    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
     and
    -1.48
     at
    -1.30
     as
    -1.30
     throughout
    -1.30
     extraordinarily
    -1.20
     on
    -1.20
     wichtigste
    -1.13
     during
    -1.11
     in
    -1.10
     appeared
    -1.09
    POSITIVE LOGITS
     другие
    1.30
    being
    1.16
    its
    1.15
    Maintenant
    1.13
     médicaux
    1.13
    simply
    1.11
     they
    1.08
    enedor
    1.08
    avoir
    1.07
    Mostrar
    1.06
    Activations Density 0.132%

    No Known Activations