© 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. 72094
    Prev
    Next
    INDEX
    Explanations

    from...to and between

    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
     seigneur
    -1.25
     zijne
    -1.25
     them
    -1.20
     their
    -1.19
     geburtstag
    -1.12
    ANAS
    -1.10
     looms
    -1.09
     mijne
    -1.09
    mathrm
    -1.07
     asing
    -1.07
    POSITIVE LOGITS
     along
    1.52
     between
    1.31
     in
    1.30
     Including
    1.27
     latter
    1.27
     /=
    1.26
     destes
    1.25
     그리고
    1.19
    étit
    1.19
     around
    1.19
    Activations Density 0.076%

    No Known Activations