© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58079
    Prev
    Next
    INDEX
    Explanations

    "то" then

    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
     and
    -2.81
    },
    -1.95
    #,
    -1.72
    netje
    -1.70
    <td>
    -1.62
    oused
    -1.61
     Stade
    -1.59
    '));
    -1.59
    +};
    -1.57
     sogar
    -1.55
    POSITIVE LOGITS
     most
    1.73
     sicheren
    1.68
     by
    1.68
     prakty
    1.59
     until
    1.59
    4
    1.57
    5
    1.57
     this
    1.55
     there
    1.53
     probably
    1.53
    Activations Density 0.012%

    No Known Activations