© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43666
    Prev
    Next
    INDEX
    Explanations

    bit set masks

    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
    Uno
    -1.48
    ging
    -1.45
    🪐
    -1.45
    E
    -1.37
     aldea
    -1.36
    壟
    -1.36
    Ț
    -1.34
     Diez
    -1.34
    "(
    -1.32
    "'
    -1.31
    POSITIVE LOGITS
     muñeco
    1.60
     you
    1.58
    ㆁ
    1.55
    夀
    1.52
     clínicas
    1.51
    isés
    1.48
    nữ
    1.47
     Работа
    1.47
    ⑉
    1.47
     monstruo
    1.45
    Activations Density 0.018%

    No Known Activations