© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10720
    Prev
    Next
    INDEX
    Explanations

    charities and philanthropy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Symmetric
    0.88
     deprecated
    0.87
     biasing
    0.86
     ancestor
    0.84
    ymmetric
    0.83
    器件
    0.81
    🅿
    0.80
    🦕
    0.78
    ymmetry
    0.78
    isotropic
    0.77
    POSITIVE LOGITS
     charities
    1.73
     Charity
    1.68
     charity
    1.60
     philanthrop
    1.56
     donations
    1.55
     nonprofits
    1.38
     charitable
    1.38
     Charities
    1.36
     philanthropy
    1.35
     philanthropic
    1.35
    Activations Density 0.072%

    No Known Activations