© 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. 211555
    Prev
    Next
    INDEX
    Explanations

    interested inimages search

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

    Backrooms and rooms

    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
     Jules
    0.58
     When
    0.46
    ➵
    0.46
     তোমার
    0.45
     TIME
    0.45
     时间
    0.45
    将
    0.45
     Thomson
    0.44
     時間
    0.44
     MAKE
    0.44
    POSITIVE LOGITS
     substituents
    0.51
     সুরক্ষা
    0.50
     subalgebras
    0.50
     ഘ
    0.47
    흄
    0.46
     compd
    0.46
    လမ်း
    0.45
     catalytic
    0.44
    されています
    0.44
    됨
    0.44
    Activations Density 0.002%

    No Known Activations