© 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. 67916
    Prev
    Next
    INDEX
    Explanations

    percentages, tourist arrivals, social networks

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

    Lower skill, encrypt, paint

    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
     RDS
    0.51
     esperamos
    0.51
     olacaktır
    0.49
    我们也
    0.48
    ພວກເຮ
    0.48
    우리
    0.48
     youll
    0.48
     ProRes
    0.47
     Radiat
    0.47
    ᱖
    0.46
    POSITIVE LOGITS
    ER
    0.52
    fe
    0.49
    ANG
    0.48
    eren
    0.48
    EN
    0.47
    ens
    0.46
    ense
    0.46
    epan
    0.46
    uth
    0.45
    _
    0.45
    Activations Density 0.002%

    No Known Activations