© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 137570
    Prev
    Next
    INDEX
    Explanations

    different than usual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oftentimes
    0.67
     аудио
    0.67
     जिसकी
    0.65
    І
    0.64
    тт
    0.63
     म्हणूनच
    0.63
     നിൽ
    0.61
    probably
    0.61
    internet
    0.61
     ನೋಡ
    0.61
    POSITIVE LOGITS
    be
    0.63
    W
    0.60
    de
    0.60
     has
    0.59
    Mu
    0.59
      
    0.58
    v
    0.57
     *
    0.56
    ва
    0.56
    M
    0.56
    Activations Density 0.003%

    No Known Activations