© 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. 44724
    Prev
    Next
    INDEX
    Explanations

    ellipsis and ranges

    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
    市の
    -1.76
    有两
    -1.66
     they
    -1.62
     when
    -1.48
    ,”
    -1.44
    eeeeeeee
    -1.41
     indicando
    -1.41
     if
    -1.40
     linke
    -1.40
     while
    -1.39
    POSITIVE LOGITS
    梛
    1.59
     escote
    1.52
     farba
    1.51
     taky
    1.51
     Gegensatz
    1.48
     tady
    1.48
     ministra
    1.45
    范文
    1.45
     kağı
    1.44
     çantası
    1.44
    Activations Density 0.019%

    No Known Activations