© 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. 12877
    Prev
    Next
    INDEX
    Explanations

    to followed by a word

    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
    有两
    -1.43
     годом
    -1.42
     哪些
    -1.41
    кнуть
    -1.41
     by
    -1.39
     ecru
    -1.38
    kün
    -1.38
     auster
    -1.37
     doughnut
    -1.37
    sibilidade
    -1.36
    POSITIVE LOGITS
     them
    1.97
     Gegensatz
    1.87
     Vordergrund
    1.84
    𓁹
    1.84
     usual
    1.81
     what
    1.80
    Its
    1.70
     üblichen
    1.66
    蚨
    1.64
     other
    1.63
    Activations Density 0.043%

    No Known Activations