© 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. 183076
    Prev
    Next
    INDEX
    Explanations

    placement, attachment, installation

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

    specific type

    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
     РАН
    0.52
    ーリー
    0.50
    海军
    0.50
     ран
    0.48
    இவர்
    0.48
     Виктор
    0.46
    անում
    0.46
    🚦
    0.46
    ավ
    0.45
    위
    0.44
    POSITIVE LOGITS
     tablecloth
    0.54
     purch
    0.52
     ona
    0.51
     crockery
    0.51
     refills
    0.50
     lingerie
    0.50
     purchase
    0.50
     cooker
    0.50
     merch
    0.49
     appliance
    0.49
    Activations Density 0.001%

    No Known Activations