© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11516
    Prev
    Next
    INDEX
    Explanations

    father of the heavenly lights

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

    compassion, kindness, yourself

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     K
    0.65
     M
    0.64
     MUSIC
    0.61
     E
    0.59
     Music
    0.54
     Para
    0.54
     U
    0.53
     There
    0.53
     W
    0.52
     Y
    0.52
    POSITIVE LOGITS
    setzen
    0.58
    жер
    0.55
    щее
    0.51
    whereas
    0.49
    reuses
    0.49
    oners
    0.48
    )},\
    0.48
    жде
    0.48
    জ্
    0.47
    쫀득
    0.47
    Activations Density 0.010%

    No Known Activations