© 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. 79410
    Prev
    Next
    INDEX
    Explanations

    episode titles and song titles

    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
     английском
    -0.92
    ffle
    -0.90
    ford
    -0.88
    ーキング
    -0.82
     мост
    -0.80
    ENCH
    -0.80
    zī
    -0.80
    ßen
    -0.78
     задний
    -0.77
     женская
    -0.77
    POSITIVE LOGITS
    raujo
    0.85
     episodio
    0.85
     発
    0.81
    🧣
    0.79
     mendengar
    0.77
    талия
    0.77
     PILL
    0.77
     titres
    0.77
    тические
    0.76
    ticians
    0.75
    Activations Density 0.039%

    No Known Activations