© 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. 20558
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

    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
     be
    -1.52
    ANCHE
    -1.48
    ėjimo
    -1.45
     betaling
    -1.43
     germain
    -1.41
     Septembre
    -1.41
     CascadeType
    -1.40
     suministros
    -1.38
     Octobre
    -1.38
     Cinéma
    -1.37
    POSITIVE LOGITS
     about
    1.90
     with
    1.84
     on
    1.71
    </h4>
    1.51
    ↵↵
    1.48
     more
    1.45
     a
    1.44
     in
    1.44
     indispensable
    1.40
     größte
    1.38
    Activations Density 0.056%

    No Known Activations