© 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. 7729
    Prev
    Next
    INDEX
    Explanations

    that noun

    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
    きち
    -2.52
    君は
    -2.30
    怎么能
    -2.23
    ਃ
    -2.19
    咴
    -2.17
    荩
    -2.09
    㠀
    -2.09
    嗬
    -2.09
    螽
    -2.06
     لأن
    -2.03
    POSITIVE LOGITS
    (!__
    2.56
    r
    2.30
    n
    2.23
    “
    2.22
    l
    2.05
    「
    2.05
    т
    1.98
    x
    1.98
     ‘
    1.83
    p
    1.78
    Activations Density 0.084%

    No Known Activations