© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70447
    Prev
    Next
    INDEX
    Explanations

    HTML table structure

    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
    綽
    -1.32
     TAMBIÉN
    -1.28
    xFFFFFF
    -1.27
     on
    -1.27
     after
    -1.27
    我怎么
    -1.23
     atencion
    -1.21
     allerede
    -1.16
     or
    -1.16
     belangrij
    -1.15
    POSITIVE LOGITS
     hins
    1.28
    yors
    1.21
     abonnement
    1.18
     Konink
    1.16
     Abon
    1.16
    erobic
    1.16
     appels
    1.16
     behar
    1.15
     uruguay
    1.13
     pamoja
    1.13
    Activations Density 0.241%

    No Known Activations