© 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. 84091
    Prev
    Next
    INDEX
    Explanations

    size, length, age

    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
    Hotline
    -1.60
     gekocht
    -1.45
     an
    -1.43
     betek
    -1.41
    langkah
    -1.40
     prachtig
    -1.40
    樯
    -1.38
     “,
    -1.32
    middag
    -1.31
     Tentang
    -1.30
    POSITIVE LOGITS
     continue
    1.57
     embora
    1.55
     precisamos
    1.53
    ANIEL
    1.52
    ن
    1.52
     если
    1.52
     continú
    1.44
    if
    1.43
     материала
    1.42
     Jahrhunder
    1.42
    Activations Density 0.068%

    No Known Activations