© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62726
    Prev
    Next
    INDEX
    Explanations

    Mi followed by specific endings

    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_34/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
     wth
    -0.76
     souhaitez
    -0.73
     enfermera
    -0.71
    тник
    -0.71
     gefertigt
    -0.71
    ঔ
    -0.71
    版本的
    -0.69
    pentru
    -0.68
     değişti
    -0.68
    ampunk
    -0.68
    POSITIVE LOGITS
     Mi
    1.20
    Mi
    1.13
     mi
    0.99
     MI
    0.94
    MIS
    0.85
     ミ
    0.79
    ufficient
    0.77
     MIS
    0.76
     mie
    0.75
     struct
    0.75
    Activations Density 0.054%

    No Known Activations