© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59223
    Prev
    Next
    INDEX
    Explanations

    people and rights

    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
     shortly
    -0.90
     عليه
    -0.90
     started
    -0.88
    adne
    -0.85
     rudimentary
    -0.82
     Shortly
    -0.82
     implementing
    -0.78
     розта
    -0.77
     drastically
    -0.77
     JUST
    -0.77
    POSITIVE LOGITS
     insieme
    1.00
    fören
    0.96
    wości
    0.95
    }\}
    0.93
    pausal
    0.93
    uges
    0.92
    alist
    0.87
    captain
    0.87
     इन
    0.86
     gebo
    0.86
    Activations Density 0.006%

    No Known Activations