© 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. 67227
    Prev
    Next
    INDEX
    Explanations

    someone and what follows

    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
     '
    -2.50
     nových
    -2.45
    ſſel
    -2.42
    🫱
    -2.30
    ekš
    -2.28
     otras
    -2.20
    ด์
    -2.20
    🫘
    -2.17
     vielen
    -2.14
     llorando
    -2.14
    POSITIVE LOGITS
    獃
    2.63
    檮
    2.33
    that
    2.31
    もありますが
    2.30
    迨
    2.30
     For
    2.28
     termed
    2.20
     撮っ
    2.20
    反应过来
    2.19
    けれ
    2.17
    Activations Density 0.011%

    No Known Activations