© 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. 859
    Prev
    Next
    INDEX
    Explanations

    Q and A format

    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
     whose
    -0.87
     get
    -0.84
     Millennium
    -0.82
    VENTION
    -0.82
    скую
    -0.82
    ！）
    -0.81
     déclaré
    -0.81
     then
    -0.79
     Sometimes
    -0.79
     genaue
    -0.78
    POSITIVE LOGITS
     strikingly
    0.96
     exceedingly
    0.93
     splendid
    0.92
     remarkably
    0.91
     instilled
    0.89
    ズキ
    0.88
    itus
    0.88
     amazingly
    0.86
    壑
    0.86
    voller
    0.85
    Activations Density 0.000%

    No Known Activations