© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119818
    Prev
    Next
    INDEX
    Explanations

    specific project names and entities

    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
    ⎔
    -1.52
     rêves
    -1.52
     kabát
    -1.48
    [>
    -1.44
     luxus
    -1.42
    Ꮸ
    -1.42
    tacos
    -1.40
    mvvm
    -1.39
     controles
    -1.38
    jennifer
    -1.34
    POSITIVE LOGITS
     by
    1.92
     I
    1.53
    p
    1.51
    to
    1.41
    Рекомен
    1.39
    when
    1.38
     It
    1.30
     first
    1.30
    re
    1.27
     M
    1.27
    Activations Density 0.330%

    No Known Activations