© 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. 99105
    Prev
    Next
    INDEX
    Explanations

    names followed by related words

    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
    {
    -3.47
    0
    -3.05
    k
    -2.64
    \
    -2.61
    '
    -2.27
     بنات
    -2.25
    m
    -2.23
     After
    -2.20
    绚
    -2.17
    啻
    -2.16
    POSITIVE LOGITS
     momentan
    2.70
    Ꮚ
    2.67
    fficking
    2.66
    うちの
    2.66
    有种
    2.61
    缯
    2.59
     étanche
    2.56
    饪
    2.52
    ꜆
    2.50
    
    2.45
    Activations Density 0.017%

    No Known Activations