© 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. 106397
    Prev
    Next
    INDEX
    Explanations

    safety should

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

    levels of robustness and subtlety

    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
    '
    0.47
     Continental
    0.46
    িগুণ
    0.45
    apping
    0.44
     ourselves
    0.44
     Northern
    0.44
     Detroit
    0.43
    ίνη
    0.43
    ieving
    0.43
    ="
    0.42
    POSITIVE LOGITS
     gambar
    0.52
     vasena
    0.51
     decency
    0.50
     sacerdote
    0.50
     berbah
    0.50
     isotherms
    0.47
     gacchati
    0.45
     ngôn
    0.45
     sarees
    0.45
     ámbito
    0.45
    Activations Density 0.003%

    No Known Activations