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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53727
    Prev
    Next
    INDEX
    Explanations

    severe toxic reaction

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

    Basic concept or Predictive modeling

    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
    Not in Any Lists

    No Comments

    Negative Logits
     కని
    0.46
     dissipation
    0.43
    0.43
     হে
    0.42
    ку
    0.42
    <h2>
    0.41
     разру
    0.41
     производится
    0.41
     settling
    0.41
     కనిప
    0.41
    POSITIVE LOGITS
    ن
    0.54
     পারা
    0.52
    aten
    0.46
    рых
    0.45
    rix
    0.44
     ומ
    0.44
    د
    0.44
    ull
    0.44
    শ্ত
    0.44
     isop
    0.43
    Activations Density 0.000%

    No Known Activations