© 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. 10-GEMMASCOPE-RES-131K
    7. 84387
    Prev
    Next
    INDEX
    Explanations

    paramount importance or PlayStation gaming

    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
    "
    -2.47
     将
    -2.41
    1
    -2.19
     dasarnya
    -2.16
    (
    -2.13
     praktisch
    -2.11
     passende
    -2.09
     кух
    -2.03
     が
    -1.99
     ..............
    -1.90
    POSITIVE LOGITS
    最后由
    3.36
    。“
    2.81
    KommentareTeilen
    2.80
     excruciating
    2.55
    。《
    2.53
    </sup>
    2.45
    除此
    2.44
    轵
    2.44
     хто
    2.44
     ominous
    2.44
    Activations Density 0.004%

    No Known Activations