© 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. 201277
    Prev
    Next
    INDEX
    Explanations

    giving and receiving valuable things

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

    philanthropy, charity, donations

    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
    楝
    0.49
    ネン
    0.48
    𒌆
    0.47
    ረጋ
    0.44
    Isopropyl
    0.44
     nhẹ
    0.43
     ಗುಣ
    0.42
     zlep
    0.42
    摂
    0.41
     です
    0.41
    POSITIVE LOGITS
     charity
    0.61
     philanthropist
    0.60
    慈善
    0.59
     philanthropic
    0.54
     auctioned
    0.53
     Charities
    0.52
     webcast
    0.52
     philanthropy
    0.51
     UNICEF
    0.51
     philanthrop
    0.51
    Activations Density 0.287%

    No Known Activations