© 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. 10-GEMMASCOPE-RES-131K
    7. 71149
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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_10/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
     akin
    -2.59
    the
    -2.25
    ''
    -2.17
     a
    -2.16
     it
    -2.06
    from
    -1.99
    would
    -1.99
    o
    -1.95
    being
    -1.93
    ”
    -1.90
    POSITIVE LOGITS
    ейчас
    2.48
     It
    2.42
    "،
    2.36
    饪
    2.20
     unknow
    2.17
     แต่
    2.16
    sprzedam
    2.16
     individuelle
    2.09
     collectible
    2.09
     ideen
    2.03
    Activations Density 0.411%

    No Known Activations