© 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. 148811
    Prev
    Next
    INDEX
    Explanations

    Instead consider

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

    sentience, error, Proto, history, parrot

    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
    Not in Any Lists

    No Comments

    Negative Logits
    哦
    0.46
    인
    0.44
     охо
    0.42
    呼
    0.42
    💏
    0.42
     independent
    0.41
     relatives
    0.41
    독
    0.41
    antro
    0.40
     diligently
    0.40
    POSITIVE LOGITS
     którą
    0.46
     ción
    0.46
     هاي
    0.45
     élytres
    0.43
     මහ
    0.42
    症状
    0.41
     élo
    0.41
     densément
    0.41
     vlak
    0.40
     trás
    0.40
    Activations Density 0.001%

    No Known Activations