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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14577
    Prev
    Next
    INDEX
    Explanations

    hotel, star, average, boutique

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

    rest after then

    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_16k_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
     Такой
    0.49
    但我
    0.47
     하지만
    0.46
    쇤
    0.46
    ెంట్
    0.46
    킬
    0.45
    하지만
    0.45
    Dialogue
    0.44
    ровали
    0.44
    현재
    0.44
    POSITIVE LOGITS
             
    0.49
     int
    0.45
               
    0.45
     vỏ
    0.45
     kø
    0.44
     wz
    0.44
              
    0.43
     sonucu
    0.43
     bên
    0.43
     hems
    0.42
    Activations Density 0.001%

    No Known Activations