© 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. 45341
    Prev
    Next
    INDEX
    Explanations

    names starting with O

    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
    []}
    -0.88
     O
    -0.87
     człowie
    -0.85
    您好
    -0.82
    ʜ
    -0.82
     oxygen
    -0.81
    これは
    -0.80
    子供の
    -0.79
     zainteres
    -0.78
    arono
    -0.77
    POSITIVE LOGITS
     sélectionnez
    0.71
     vpon
    0.71
    fires
    0.71
     بدأ
    0.69
    favor
    0.69
     будто
    0.69
    cling
    0.68
    ruary
    0.68
     Utd
    0.67
    Demi
    0.67
    Activations Density 0.027%

    No Known Activations