© 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. 57056
    Prev
    Next
    INDEX
    Explanations

    Drama Desk Award

    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
     kän
    -0.78
     habrían
    -0.74
     можно
    -0.72
    haviour
    -0.71
    St
    -0.71
    僕
    -0.71
     preferencia
    -0.69
     göm
    -0.69
    אָ
    -0.68
    Can
    -0.68
    POSITIVE LOGITS
     vise
    0.92
     uti
    0.91
     ales
    0.90
     Achievements
    0.88
    ファミ
    0.86
     tug
    0.84
     DECLARATION
    0.84
    ネジ
    0.84
    lorette
    0.82
    GAP
    0.82
    Activations Density 0.003%

    No Known Activations