© 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. 22-GEMMASCOPE-RES-131K
    7. 25127
    Prev
    Next
    INDEX
    Explanations

    parole officer, prophecies, forest, teenager

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ημέ
    -1.13
    恚
    -1.04
     czasem
    -1.02
    헷
    -0.99
    setTo
    -0.99
     pernicious
    -0.99
     many
    -0.98
    のだろうか
    -0.97
     Prozesse
    -0.96
     TOPOLOGY
    -0.96
    POSITIVE LOGITS
     плохо
    1.17
    parently
    1.13
    convenient
    1.11
    apparently
    1.09
    ⸫
    1.07
     deux
    1.04
    obviously
    1.03
     seçenek
    1.02
    mschrijving
    1.02
     básicamente
    0.99
    Activations Density 0.034%

    No Known Activations