© 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. 22-GEMMASCOPE-RES-131K
    7. 13924
    Prev
    Next
    INDEX
    Explanations

    type of occupation or field

    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_22/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
     by
    -1.20
    による
    -1.11
    Väl
    -0.99
    有機
    -0.98
    stwa
    -0.98
    枓
    -0.97
     uży
    -0.97
     various
    -0.97
     multiple
    -0.96
    Numerous
    -0.96
    POSITIVE LOGITS
     type
    1.31
     typu
    1.26
     THOSE
    1.19
     chcete
    1.17
     eenen
    1.13
     specialization
    1.11
    juang
    1.09
     musíte
    1.09
     explosión
    1.04
    fying
    1.03
    Activations Density 0.060%

    No Known Activations