© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28059
    Prev
    Next
    INDEX
    Explanations

    while followed by dating or dimensions

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

    trying to do or change

    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
    '}$
    0.46
    誓
    0.46
     edilir
    0.45
    ziehungen
    0.44
    宄
    0.44
    スコ
    0.43
     Educators
    0.43
     educator
    0.42
     содержит
    0.42
     organizes
    0.42
    POSITIVE LOGITS
     Melo
    0.52
     leisure
    0.51
    r
    0.51
    ຣ
    0.50
     turismo
    0.50
     nuo
    0.49
     meny
    0.49
     contactless
    0.49
     rosé
    0.48
     เรีย
    0.47
    Activations Density 0.000%

    No Known Activations