© 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. 108152
    Prev
    Next
    INDEX
    Explanations

    results after best

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

    rigidly adhering

    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
    法令
    0.52
    ୌ
    0.50
    ⿹
    0.50
     única
    0.50
    零件
    0.50
    棪
    0.49
    六年
    0.48
    сным
    0.48
    য
    0.47
     başarı
    0.47
    POSITIVE LOGITS
     exceeding
    0.44
     clichés
    0.44
     AIDS
    0.43
    assistance
    0.43
     gratuitamente
    0.42
    ive
    0.41
    uous
    0.41
    輯
    0.41
     indulgent
    0.41
    輒
    0.41
    Activations Density 0.001%

    No Known Activations