© 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. 68710
    Prev
    Next
    INDEX
    Explanations

    inverse or reciprocal

    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
    Negative Logits
    </i>
    -1.59
     have
    -1.54
     originalmente
    -1.48
    されていた
    -1.42
    子が
    -1.38
    <bos>
    -1.35
    ⎘
    -1.34
     was
    -1.31
     and
    -1.26
    ’,
    -1.23
    POSITIVE LOGITS
     さ
    1.78
    烀
    1.63
     trataba
    1.62
    There
    1.59
    踅
    1.58
    媖
    1.57
     Instead
    1.55
    cherichia
    1.54
     indisponible
    1.49
     décédé
    1.49
    Activations Density 0.017%

    No Known Activations