© 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. 22-GEMMASCOPE-RES-131K
    7. 129427
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting pairs

    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_22/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
     TAMBÉM
    -1.84
     Dinas
    -1.38
     meilleures
    -1.37
     Fiscalía
    -1.33
     contenedores
    -1.32
     elegante
    -1.30
     diámetro
    -1.30
     vacía
    -1.30
     coûts
    -1.29
     เปิด
    -1.29
    POSITIVE LOGITS
     an
    1.92
     more
    1.75
     any
    1.63
     two
    1.48
     one
    1.48
     several
    1.46
     both
    1.41
     our
    1.41
     during
    1.38
     its
    1.37
    Activations Density 0.079%

    No Known Activations