© 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-262K
    7. 90308
    Prev
    Next
    INDEX
    Explanations

    sub, AFC, MTV, rivers, primarily, generally, posible

    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_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
    \
    0.44
    rown
    0.43
    Í
    0.41
    th
    0.41
     Stre
    0.41
    ↵↵
    0.40
    thon
    0.39
    [
    0.39
    upt
    0.38
    men
    0.38
    POSITIVE LOGITS
     turkeys
    0.48
     photons
    0.47
     erythrocytes
    0.46
     syntactic
    0.45
    ❶
    0.45
     tulips
    0.44
     glycoproteins
    0.44
     percolation
    0.43
     coalgebras
    0.43
     morphisms
    0.42
    Activations Density 0.001%

    No Known Activations