© 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. 211839
    Prev
    Next
    INDEX
    Explanations

    Hacker App, root script, savory fillings

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

    path to

    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
    ἡ
    0.45
     zoals
    0.44
    менти
    0.43
     Context
    0.42
    бую
    0.41
     Yale
    0.41
     entirety
    0.41
     identificación
    0.40
     Drawing
    0.40
    ক্ষিতে
    0.40
    POSITIVE LOGITS
    स
    0.50
    Cré
    0.47
    द
    0.46
     सिंगल
    0.45
    It
    0.45
    senha
    0.45
     लीक
    0.45
     rumours
    0.44
    eksiyon
    0.43
    PORTS
    0.43
    Activations Density 0.005%

    No Known Activations