© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5140
    Prev
    Next
    INDEX
    Explanations

    RA, RR, Reuters, Ruby, rational, rectum

    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_31_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
     Львів
    0.77
    u
    0.71
     ০
    0.70
     salen
    0.70
     ταιν
    0.70
    ä
    0.64
     πραγμα
    0.61
     adiabatically
    0.61
    म
    0.60
     précédentes
    0.59
    POSITIVE LOGITS
    al
    0.90
    getR
    0.80
    ،
    0.71
     R
    0.65
    all
    0.64
    R
    0.64
     Rumble
    0.64
    ى
    0.63
    RO
    0.62
    ны
    0.61
    Activations Density 1.447%

    No Known Activations