© 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. 176505
    Prev
    Next
    INDEX
    Explanations

    seasonal hours

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

    understanding or courses

    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
     Zeitung
    0.53
    ውነ
    0.53
    രുവന
    0.49
    Glu
    0.49
    chten
    0.48
    และ
    0.46
    ikkh
    0.46
    ท
    0.46
    பிலோ
    0.46
     Амери
    0.45
    POSITIVE LOGITS
     foreclose
    0.50
     burn
    0.49
     a
    0.47
     isn
    0.47
     length
    0.45
    nee
    0.45
     compute
    0.45
     you
    0.45
     aa
    0.45
     space
    0.44
    Activations Density 0.001%

    No Known Activations