© 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. 15831
    Prev
    Next
    INDEX
    Explanations

    locations after of

    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
    );
    -1.69
    他说
    -1.63
    蓠
    -1.60
    ܜ
    -1.55
     anledning
    -1.53
     určit
    -1.52
     tästä
    -1.51
    ],
    -1.51
     artikke
    -1.47
     $
    -1.43
    POSITIVE LOGITS
     but
    1.41
     öst
    1.39
     لكن
    1.39
     elsewhere
    1.38
    出来て
    1.38
    endra
    1.38
     It
    1.38
     soziale
    1.37
     addresses
    1.34
    嫫
    1.34
    Activations Density 0.004%

    No Known Activations