© 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. 95601
    Prev
    Next
    INDEX
    Explanations

    great depression

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

    image descriptions

    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
    p
    0.56
     Responsible
    0.50
     Responsibility
    0.49
     Awareness
    0.47
    bli
    0.47
    s
    0.47
    display
    0.45
    v
    0.44
    displayed
    0.44
     Communicate
    0.43
    POSITIVE LOGITS
    ו
    0.62
     todas
    0.58
    رات
    0.52
     wszystkie
    0.52
     ventanas
    0.52
     piedras
    0.50
    و
    0.50
     peces
    0.49
     ataques
    0.49
     всё
    0.48
    Activations Density 0.000%

    No Known Activations