© 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. 16508
    Prev
    Next
    INDEX
    Explanations

    HTML and code tags

    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
     to
    -1.53
    izzati
    -1.30
     ilgi
    -1.30
    lampe
    -1.27
     katk
    -1.26
    ໊
    -1.24
     traditionelle
    -1.23
    tisgarh
    -1.18
    szcz
    -1.18
    ventes
    -1.15
    POSITIVE LOGITS
    ↵↵
    1.23
    .
    1.21
    !
    1.13
    ?
    1.08
    ↵
    1.06
    や
    1.03
    9
    1.01
    </h4>
    1.00
    \
    0.96
    The
    0.94
    Activations Density 0.002%

    No Known Activations