© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7148
    Prev
    Next
    INDEX
    Explanations

    charitable donations and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     Ribeiro
    1.04
    潰
    0.94
    溃
    0.93
    轿
    0.91
    缉
    0.88
     Navarro
    0.87
     boot
    0.87
     jobless
    0.87
     detention
    0.85
     Disk
    0.84
    POSITIVE LOGITS
     donors
    2.40
     Donor
    2.37
    Donor
    2.37
     donor
    2.34
     donating
    2.29
     donation
    2.22
     donations
    2.20
    donor
    2.17
     donate
    2.12
    捐
    2.12
    Activations Density 0.421%

    No Known Activations