© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    谞
    -1.45
     необхідно
    -1.37
    Kommentar
    -1.37
    bren
    -1.35
    tigheter
    -1.35
    Preise
    -1.34
    Kritik
    -1.33
    Mitar
    -1.32
    Perú
    -1.30
    不可能
    -1.29
    POSITIVE LOGITS
     also
    1.45
     –
    1.45
     bahkan
    1.43
     even
    1.40
    mathrm
    1.36
    
    1.35
     who
    1.34
     thema
    1.29
     Ślą
    1.28
     даже
    1.27
    Activations Density 0.068%

    No Known Activations