© 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. 34-GEMMASCOPE-RES-131K
    7. 29907
    Prev
    Next
    INDEX
    Explanations

    observable

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    满了
    -0.81
    entid
    -0.76
    Nhap
    -0.73
     geschützt
    -0.73
    pensive
    -0.70
    Protected
    -0.69
    помним
    -0.69
    vení
    -0.68
     Harry
    -0.68
     rutina
    -0.66
    POSITIVE LOGITS
     Observable
    2.61
    Observable
    2.55
     observable
    1.97
    observable
    1.94
    Observ
    1.72
     Observ
    1.63
     stream
    1.60
     observa
    1.59
     observables
    1.54
     OBSERV
    1.49
    Activations Density 0.038%

    No Known Activations