© 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. 16767
    Prev
    Next
    INDEX
    Explanations

    definition or variable assignment

    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
     others
    -1.24
    ׳
    -1.17
    AnchorStyles
    -1.15
     poderão
    -1.13
     another
    -1.12
     confortável
    -1.10
    其他
    -1.09
    ༷
    -1.09
     other
    -1.09
     terão
    -1.07
    POSITIVE LOGITS
     принад
    1.15
    代わりに
    1.05
     понадоби
    1.04
     нада
    1.03
    <bos>
    1.02
     люб
    1.02
    It
    1.00
    Antwoord
    0.99
    それだけ
    0.99
    </b>
    0.98
    Activations Density 0.001%

    No Known Activations