© 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. 23802
    Prev
    Next
    INDEX
    Explanations

    proceeds benefit charities

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

    charitable aid and community support

    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
     設計
    0.47
    FRAGMENT
    0.47
     chromatographic
    0.46
     керу
    0.46
     位置
    0.45
     透
    0.45
     নিশ্চ
    0.45
    丁寧
    0.44
     でしょう
    0.44
     変
    0.43
    POSITIVE LOGITS
     charity
    0.95
     charities
    0.90
     Charities
    0.75
     charitable
    0.71
     Charity
    0.71
     fundraising
    0.69
    慈善
    0.65
     underprivileged
    0.65
     benefiting
    0.62
    cancer
    0.61
    Activations Density 0.139%

    No Known Activations