© 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. 98517
    Prev
    Next
    INDEX
    Explanations

    main

    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
    鲠
    -0.93
    nere
    -0.92
    женские
    -0.91
    iseks
    -0.91
    Tinh
    -0.90
    genus
    -0.90
    gamos
    -0.89
    ه‌ی
    -0.87
    </h3>
    -0.87
     Strongly
    -0.84
    POSITIVE LOGITS
    tainer
    1.66
    tained
    1.63
    frame
    1.53
    stays
    1.52
    tains
    1.29
    TAIN
    1.21
    tainers
    1.20
     artery
    1.19
    stay
    1.18
    taining
    1.16
    Activations Density 0.053%

    No Known Activations