© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1672
    Prev
    Next
    INDEX
    Explanations

    biblical statements and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
     tajem
    0.26
     kumpulan
    0.25
     mø
    0.24
     cuisson
    0.24
     madeira
    0.23
     silencio
    0.23
    <unused242>
    0.23
     pessoa
    0.23
    
    0.23
    }/\
    0.23
    POSITIVE LOGITS
    Therefore
    0.26
     therefore
    0.25
    adians
    0.25
     Therefore
    0.24
     Indeed
    0.24
     writes
    0.23
     Ephesians
    0.23
    Indeed
    0.22
     κάνει
    0.21
    Write
    0.21
    Activations Density 0.004%

    No Known Activations