© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30517
    Prev
    Next
    INDEX
    Explanations

    UI grouping and collapsible sections

    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
    könyv
    -0.83
    dov
    -0.80
    注册
    -0.76
    softmax
    -0.76
    tellungs
    -0.76
    道具
    -0.72
     downloading
    -0.72
    nelles
    -0.72
    Downloading
    -0.72
    stmt
    -0.71
    POSITIVE LOGITS
     groupBox
    0.96
    groupBox
    0.91
     title
    0.88
     collapse
    0.88
    GroupBox
    0.82
     GATE
    0.80
    collapse
    0.77
     legend
    0.77
    ).__
    0.75
    lapsible
    0.74
    Activations Density 0.001%

    No Known Activations