© 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. 80715
    Prev
    Next
    INDEX
    Explanations

    laid out, laid back, laid in

    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
    蕷
    -2.66
     でも
    -2.41
    e
    -2.30
    replyreport
    -2.27
     seven
    -2.23
     guerras
    -2.19
     beeintr
    -2.17
     seventeen
    -2.09
    J
    -2.09
    ﾄ
    -2.08
    POSITIVE LOGITS
    '
    3.11
    </strong>
    2.50
    さっき
    2.31
    、“
    2.23
    嗫
    2.16
     tiveram
    2.16
    臵
    2.16
    乆
    2.11
     geha
    2.09
     setelan
    2.06
    Activations Density 0.005%

    No Known Activations