© 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. 73226
    Prev
    Next
    INDEX
    Explanations

    vert and similar 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
    
    -2.83
     Houſe
    -2.66
     greateſt
    -2.45
     одном
    -2.30
    vantaged
    -2.28
     We
    -2.23
    ти
    -2.22
    middel
    -2.20
     erwähnten
    -2.19
    ca
    -2.17
    POSITIVE LOGITS
    龵
    2.89
    ︲
    2.81
    他有
    2.56
     nourished
    2.53
    ╿
    2.53
    
    2.52
    ственные
    2.52
    If
    2.50
    ╽
    2.50
    ſelf
    2.48
    Activations Density 0.001%

    No Known Activations