© 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. 48591
    Prev
    Next
    INDEX
    Explanations

    network side, server, APP, or browser

    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
    Possibly
    -0.86
    ђа
    -0.82
    (+)
    -0.82
    aClass
    -0.81
     Viktor
    -0.81
    幌
    -0.79
    很赞
    -0.78
     LAS
    -0.77
     supaya
    -0.75
     employ
    -0.74
    POSITIVE LOGITS
    ͓
    0.96
     lụ
    0.92
     backstage
    0.89
    ваемых
    0.87
    ٗ
    0.84
    ﺬ
    0.84
     inquiries
    0.83
     enquiry
    0.83
     enquiries
    0.83
     authorization
    0.82
    Activations Density 0.028%

    No Known Activations