© 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. 70887
    Prev
    Next
    INDEX
    Explanations

    mobile users, career, houses

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

    support, CF, reproduce, long

    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
    𝖚
    0.45
    गढ़
    0.45
     acupuncture
    0.44
    厠
    0.42
    లే
    0.41
     mannen
    0.41
     сексуа
    0.40
    скага
    0.40
    壷
    0.40
     conjugacy
    0.39
    POSITIVE LOGITS
     beauties
    0.52
    الحمد
    0.50
     Serv
    0.47
     Nez
    0.47
    ROE
    0.47
    Monte
    0.46
    ANC
    0.45
     Tüm
    0.45
     Diplom
    0.44
     Ny
    0.44
    Activations Density 0.001%

    No Known Activations