© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1602
    Prev
    Next
    INDEX
    Explanations

    API response types

    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
    UpdateUser
    -0.84
    וי
    -0.82
    λον
    -0.81
     Mahatma
    -0.78
    loadMore
    -0.77
    AddUser
    -0.75
     коричне
    -0.75
    Aktual
    -0.75
    Tekst
    -0.75
    Cure
    -0.74
    POSITIVE LOGITS
     государственной
    0.85
    `
    0.82
    istique
    0.81
    辻
    0.80
    est
    0.78
    afa
    0.76
    ":
    0.75
    櫛
    0.74
    memset
    0.73
     ـ
    0.73
    Activations Density 0.050%

    No Known Activations