© 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. 68596
    Prev
    Next
    INDEX
    Explanations

    old and subsequent words

    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
     deft
    -1.73
     acoso
    -1.72
    嵛
    -1.70
    荭
    -1.68
     incorporar
    -1.67
     में
    -1.66
     desarrollando
    -1.62
    𐀀
    -1.60
     registró
    -1.59
     ofreci
    -1.58
    POSITIVE LOGITS
    }$
    1.87
    ？』
    1.73
    It
    1.73
    );
    1.67
     have
    1.67
    های
    1.66
    ヒーロー
    1.62
    ="",
    1.60
     déclare
    1.60
    ??)
    1.57
    Activations Density 0.004%

    No Known Activations