© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2492
    Prev
    Next
    INDEX
    Explanations

    moving averages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    습니다
    1.76
    rna
    1.54
    reden
    1.49
    ma
    1.49
    czas
    1.48
    स्मै
    1.47
     karna
    1.47
    Ска
    1.44
     अपन
    1.42
    র
    1.40
    POSITIVE LOGITS
     Tropical
    1.88
     illumination
    1.87
     Hydro
    1.86
     Gourmet
    1.86
     Villas
    1.85
     Ornamental
    1.85
     Cartier
    1.85
     Luxurious
    1.83
     Hôtel
    1.83
     Venice
    1.82
    Activations Density 0.000%

    No Known Activations