© 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. 10-GEMMASCOPE-RES-131K
    7. 14441
    Prev
    Next
    INDEX
    Explanations

    is believed or known

    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
    vaný
    -1.30
    ьет
    -1.27
    خواندن
    -1.25
     consegui
    -1.23
    sikker
    -1.23
     November
    -1.22
    してた
    -1.22
     kín
    -1.21
    usions
    -1.20
     señalado
    -1.20
    POSITIVE LOGITS
     of
    1.61
     oggi
    1.61
     nowadays
    1.34
     today
    1.28
    いま
    1.27
    新款
    1.25
     вашего
    1.25
     fritt
    1.22
     parlare
    1.22
    now
    1.22
    Activations Density 0.149%

    No Known Activations