© 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. 136202
    Prev
    Next
    INDEX
    Explanations

    stock market

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

    categories/focus

    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
    Tuy
    0.49
    WHEN
    0.47
    《
    0.47
    冯
    0.47
    ம்தா
    0.46
    IVE
    0.45
     assign
    0.45
     proprio
    0.44
     assunto
    0.44
    “
    0.44
    POSITIVE LOGITS
    اس
    0.47
    龰
    0.44
     transmittance
    0.44
     പി
    0.44
     Middles
    0.42
     수가
    0.41
     สี
    0.41
    zki
    0.41
     る
    0.40
    ोत्तर
    0.40
    Activations Density 0.001%

    No Known Activations