© 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. 49230
    Prev
    Next
    INDEX
    Explanations

    line up

    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
    ametros
    -0.82
     Jesse
    -0.80
    Assets
    -0.75
    sales
    -0.73
     tickets
    -0.72
     June
    -0.72
    फ्त
    -0.70
     Purple
    -0.70
    หรับ
    -0.70
     Sales
    -0.69
    POSITIVE LOGITS
    ups
    1.61
     up
    1.48
    up
    1.41
     ups
    1.35
    アップ
    1.16
    업
    1.10
    UPS
    1.07
    UP
    0.98
    upt
    0.96
    yup
    0.94
    Activations Density 0.026%

    No Known Activations