© 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. 191162
    Prev
    Next
    INDEX
    Explanations

    date, Greek, minor, kids

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

    summer trip

    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
    ingly
    0.58
    ually
    0.46
    ac
    0.45
    p
    0.43
    ivity
    0.43
     গুণে
    0.42
     voilà
    0.41
    ul
    0.40
    하였다
    0.40
     우
    0.39
    POSITIVE LOGITS
     willen
    0.49
     landen
    0.48
    ត្រូវការ
    0.48
    část
    0.47
     plaatsen
    0.47
    setLocation
    0.47
     mögliche
    0.47
    Ř
    0.46
    nehmen
    0.46
     Armenians
    0.46
    Activations Density 0.002%

    No Known Activations