© 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. 223578
    Prev
    Next
    INDEX
    Explanations

    chlorine dioxide

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

    diagnosing issues

    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
    諷
    0.46
    Nombre
    0.46
    Fonte
    0.44
    unpriv
    0.44
    ชื่อ
    0.43
    Кра
    0.42
    Nos
    0.42
    Comme
    0.41
    Upp
    0.41
    Salam
    0.41
    POSITIVE LOGITS
     层
    0.53
     unos
    0.52
     arz
    0.52
     vá
    0.50
     bakteri
    0.50
     canoe
    0.49
     patriot
    0.49
     sınıf
    0.48
    MENTS
    0.47
     Cricket
    0.47
    Activations Density 0.000%

    No Known Activations