© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184130
    Prev
    Next
    INDEX
    Explanations

    naming scheme

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

    Creator, refurbishment, code, company, clothing

    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
     I
    0.46
     but
    0.45
     with
    0.45
      
    0.44
       
    0.42
     todays
    0.42
    cribes
    0.42
    Into
    0.42
    with
    0.41
     cork
    0.41
    POSITIVE LOGITS
     উপদে
    0.53
    स्रोत
    0.51
     होत्या
    0.46
    仳
    0.46
    𒁁
    0.46
    住在
    0.46
     productividad
    0.44
     পুঁজিব
    0.44
     renormalized
    0.44
     ด่า
    0.44
    Activations Density 0.001%

    No Known Activations