© 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. 57978
    Prev
    Next
    INDEX
    Explanations

    "first" followed by components or states

    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
    橚
    -1.59
     this
    -1.57
     offiziellen
    -1.56
     eigentlichen
    -1.53
     Before
    -1.53
     vierten
    -1.51
     Além
    -1.49
     Нужно
    -1.49
     Também
    -1.48
     sogenannten
    -1.48
    POSITIVE LOGITS
     didn
    1.52
    '
    1.52
     and
    1.51
     nien
    1.49
     Tagen
    1.40
     separar
    1.38
     preparando
    1.32
     dando
    1.31
     warum
    1.31
    国产
    1.30
    Activations Density 0.068%

    No Known Activations