© 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. 211991
    Prev
    Next
    INDEX
    Explanations

    specific combinations of words

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

    Beyond takeout

    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
    l
    0.54
    splash
    0.52
    可以看出
    0.49
    observatoire
    0.48
    infiltration
    0.48
    n
    0.48
    uptime
    0.47
    an
    0.44
    izi
    0.44
    ie
    0.43
    POSITIVE LOGITS
    戙
    0.44
    یس
    0.44
    場合に
    0.44
    𝗘
    0.44
     monopol
    0.43
     sociétés
    0.43
    وق
    0.43
    ).\\
    0.43
     분석
    0.42
    连忙
    0.42
    Activations Density 0.001%

    No Known Activations