© 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. 92277
    Prev
    Next
    INDEX
    Explanations

    company names and job titles

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

    prevent excessive, maintain balance

    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
    Jeśli
    0.55
     kvůli
    0.54
    懟
    0.52
    Когда
    0.51
    因为
    0.50
    如果是
    0.50
     因为
    0.50
    是因为
    0.49
    尟
    0.49
    因為
    0.48
    POSITIVE LOGITS
     resumed
    0.60
     our
    0.52
     IT
    0.50
     three
    0.50
     XX
    0.50
     COPD
    0.49
     Know
    0.49
     provides
    0.49
     customers
    0.49
     twelve
    0.49
    Activations Density 0.002%

    No Known Activations