© 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. 117118
    Prev
    Next
    INDEX
    Explanations

    code script tags

    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
     McGregor
    -0.84
     Montes
    -0.84
    SUBJECT
    -0.78
     капю
    -0.78
     उ
    -0.77
    GERMANY
    -0.75
     potable
    -0.73
    gesetzt
    -0.73
    Santa
    -0.73
     Villa
    -0.73
    POSITIVE LOGITS
    Soorten
    0.89
     مربع
    0.85
    Balas
    0.83
    рюкзак
    0.82
    essere
    0.82
     reivindic
    0.80
     وزیر
    0.79
     lâng
    0.78
    parer
    0.78
    Préparation
    0.78
    Activations Density 0.002%

    No Known Activations