© 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. 117997
    Prev
    Next
    INDEX
    Explanations

    ergonomic discourse mother

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

    understanding how to

    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
    S
    0.59
    T
    0.46
    AN
    0.46
    RNAs
    0.45
    United
    0.45
    G
    0.45
    k
    0.44
    I
    0.44
    Premier
    0.44
    K
    0.44
    POSITIVE LOGITS
     Gemma
    0.48
    리카
    0.47
    holung
    0.47
     fatten
    0.47
    ပြန်
    0.46
    টসঅ্যাপ
    0.45
    것도
    0.45
     Cristina
    0.45
    <unused49>
    0.45
    φη
    0.45
    Activations Density 0.000%

    No Known Activations