© 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. 199209
    Prev
    Next
    INDEX
    Explanations

    seventh degree, again written, you choose

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

    entertaining ideas or present concepts

    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
     Knot
    0.48
     kombin
    0.47
     bangunan
    0.47
     gedung
    0.46
    好
    0.45
     lantai
    0.45
     pingis
    0.45
    部屋
    0.44
     throwable
    0.44
     Honeywell
    0.44
    POSITIVE LOGITS
    𝗰
    0.53
    tamil
    0.49
    actic
    0.48
    vou
    0.48
    collect
    0.47
    bfs
    0.47
    question
    0.47
    𝓼
    0.47
    Ể
    0.46
    mc
    0.46
    Activations Density 0.002%

    No Known Activations