© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70137
    Prev
    Next
    INDEX
    Explanations

    Reference 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_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
     genres
    -0.85
    larna
    -0.82
    ܕ
    -0.80
     "#{
    -0.78
    akujem
    -0.78
    jard
    -0.77
     Ně
    -0.75
    genstein
    -0.75
    셨
    -0.74
    лізу
    -0.73
    POSITIVE LOGITS
    rar
    0.76
    נפ
    0.75
    անում
    0.75
     contient
    0.74
    olás
    0.74
    ile
    0.71
    了出来
    0.71
    寥
    0.71
     montant
    0.69
    辛い
    0.68
    Activations Density 0.027%

    No Known Activations