© 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. 112545
    Prev
    Next
    INDEX
    Explanations

    revolutionize computing

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

    image and layout prompts

    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
    ی
    0.50
    ۔
    0.48
     fanno
    0.47
    Often
    0.46
    िट
    0.44
    ירות
    0.44
    ネタ
    0.43
    ють
    0.41
    罢
    0.41
    ulares
    0.41
    POSITIVE LOGITS
    jakarta
    0.50
    ongyang
    0.49
     Yogyakarta
    0.48
     planificación
    0.45
     felhasznál
    0.45
     Yukawa
    0.44
     JPL
    0.44
     NASA
    0.43
     jml
    0.43
     squadrons
    0.43
    Activations Density 0.001%

    No Known Activations