© 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. 127440
    Prev
    Next
    INDEX
    Explanations

    addresses, URLs, and phone numbers

    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
    </h4>
    -1.50
     cewek
    -1.45
     trochę
    -1.42
     ciclista
    -1.41
     palav
    -1.38
     kategori
    -1.36
     alltid
    -1.34
     pacar
    -1.34
     zima
    -1.33
     verdura
    -1.33
    POSITIVE LOGITS
     if
    1.60
     with
    1.41
     for
    1.31
    之类的
    1.30
    go
    1.29
    le
    1.29
     dipendenti
    1.25
     they
    1.24
     after
    1.24
    uu
    1.23
    Activations Density 0.120%

    No Known Activations