© 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-262K
    7. 108646
    Prev
    Next
    INDEX
    Explanations

    OLPC XO

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

    content pillars

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    \
    0.49
    tout
    0.45
    elligence
    0.44
    ilets
    0.44
    titor
    0.43
    u
    0.43
    ิญ
    0.42
    t
    0.42
     telenov
    0.40
     goodwill
    0.40
    POSITIVE LOGITS
     दिनांक
    0.48
     entsprechend
    0.47
     Nz
    0.45
    ALTERNATIV
    0.44
    かわ
    0.44
    ynie
    0.43
     concentración
    0.43
     选择
    0.43
     dated
    0.43
    SCAN
    0.41
    Activations Density 0.001%

    No Known Activations