© 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. 112731
    Prev
    Next
    INDEX
    Explanations

    explaining financial products

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

    foreign words and academic terms

    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
    in
    0.48
    Pss
    0.44
    <0xE3>
    0.42
    Us
    0.42
    佑
    0.42
    et
    0.41
    ，“
    0.41
    ウス
    0.41
    郵便
    0.40
    з
    0.40
    POSITIVE LOGITS
     entste
    0.50
     kitabı
    0.49
     ആരാ
    0.47
    aterdag
    0.46
     getan
    0.45
     ricerche
    0.45
     ખાતે
    0.44
    muse
    0.44
     zabez
    0.44
    दास
    0.43
    Activations Density 0.003%

    No Known Activations