© 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. 185058
    Prev
    Next
    INDEX
    Explanations

    assist protect

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

    given that

    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
    지
    0.44
     дели
    0.43
     تیل
    0.43
    யம்
    0.43
    sust
    0.42
    scalable
    0.42
    工夫
    0.42
    扮
    0.42
     जरा
    0.42
    探し
    0.42
    POSITIVE LOGITS
     ব্যতীত
    0.51
     బాధ
    0.48
     zwar
    0.46
     assistência
    0.46
     sowohl
    0.45
     অবৈধ
    0.45
    État
    0.44
    venir
    0.42
    ৬৮
    0.42
     συνεχ
    0.41
    Activations Density 0.002%

    No Known Activations