© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    database index definitions

    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
    another
    -1.34
     banheiro
    -1.22
     isolamento
    -1.16
     assistente
    -1.13
     adesivo
    -1.13
     saudável
    -1.12
     borbo
    -1.12
    uitable
    -1.12
    बल
    -1.08
     explanation
    -1.06
    POSITIVE LOGITS
     on
    1.55
     at
    1.39
     for
    1.20
     take
    0.98
    </h4>
    0.97
     not
    0.97
     just
    0.96
     гг
    0.96
     business
    0.96
     fil
    0.95
    Activations Density 0.003%

    No Known Activations