© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 567
    Prev
    Next
    INDEX
    Explanations

    sincerely / heartfelt / goodbye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     เป้า
    0.95
     제곱
    0.78
     iteratively
    0.76
     목표
    0.75
     มัน
    0.74
     dynamism
    0.71
     retinol
    0.70
    }}=$
    0.69
     superhuman
    0.69
     도입
    0.68
    POSITIVE LOGITS
     Funeral
    1.96
    Funeral
    1.91
     funeral
    1.89
    funeral
    1.68
     interment
    1.67
     cremation
    1.60
     Interment
    1.56
     burial
    1.55
     Burial
    1.50
     memorial
    1.40
    Activations Density 0.520%

    No Known Activations