© 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. 98519
    Prev
    Next
    INDEX
    Explanations

    Shari'a compliant stocks

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

    prompted target

    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
    ffiti
    0.49
    ý
    0.47
     fè
    0.46
    be
    0.45
    asiti
    0.44
    paw
    0.44
     considerazione
    0.44
    caso
    0.43
    ayit
    0.42
    porque
    0.42
    POSITIVE LOGITS
     Adjusted
    0.49
     سالب
    0.48
     normed
    0.47
     در
    0.46
    確認
    0.45
    以上的
    0.45
     moyennes
    0.45
    凈
    0.44
     مطابق
    0.43
    鋯
    0.43
    Activations Density 0.000%

    No Known Activations