© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114076
    Prev
    Next
    INDEX
    Explanations

    MIPS, Obamacare, golang

    np_acts-logits-general · gemini-2.5-flash-lite

    the acronym "MIPS" (either the computer architecture or maximal inspiratory pressure) or references to "Obamacare" in political contexts.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
    </i>
    -2.92
    絰
    -2.55
    </b>
    -2.41
    ጮ
    -2.34
    ;
    -2.30
    ありました
    -2.27
    釷
    -2.22
    久し
    -2.19
    她说
    -2.19
     huddled
    -2.16
    POSITIVE LOGITS
    咴
    2.94
    as
    2.78
    ↵↵
    2.73
    geſ
    2.63
    </h2>
    2.61
    ")]
    2.58
    Y
    2.53
    。
    2.44
     was
    2.41
    ."
    2.39
    Activations Density 0.020%

    No Known Activations