© 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. 108676
    Prev
    Next
    INDEX
    Explanations

    fourth quarter

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

    breakdown and asking is

    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
    parsedBlock
    0.48
     부터
    0.47
    UIButton
    0.46
     політи
    0.46
    퇸
    0.46
    υπ
    0.45
    薰
    0.45
    转换
    0.45
     Phật
    0.45
    nextSend
    0.45
    POSITIVE LOGITS
    seven
    0.46
    href
    0.46
    profile
    0.45
     institutions
    0.44
     Institutions
    0.43
     institute
    0.41
     afin
    0.41
     aesthetics
    0.40
     systematics
    0.40
    framework
    0.40
    Activations Density 0.001%

    No Known Activations