© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85678
    Prev
    Next
    INDEX
    Explanations

    saving, reducing costs

    np_acts-logits-general · gemini-2.5-flash-lite

    saving and pouring water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     einzelnen
    0.46
     semblent
    0.44
     تعداد
    0.44
     einzelne
    0.43
     Digests
    0.42
     المؤلف
    0.42
     সংখ্য
    0.41
     কয়েকজন
    0.41
     sugli
    0.41
    ǃ
    0.41
    POSITIVE LOGITS
     ahorrar
    0.47
     saving
    0.46
     reduce
    0.45
     fortitude
    0.44
    节省
    0.44
     restrain
    0.43
     avoid
    0.43
     savings
    0.43
    ир
    0.43
    節
    0.43
    Activations Density 0.004%

    No Known Activations