© 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. 221563
    Prev
    Next
    INDEX
    Explanations

    web server technology

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

    audiences, saving, research, safety

    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
    錘
    0.46
    ஷ்
    0.45
    附属
    0.44
    шей
    0.43
    лим
    0.43
    kB
    0.43
    쌀
    0.43
    ោះ
    0.42
    た
    0.42
     tun
    0.42
    POSITIVE LOGITS
     OSC
    0.46
     হয়ত
    0.44
     UNICEF
    0.44
     भ्रम
    0.44
     अडचणी
    0.44
     کمپیو
    0.44
     madame
    0.43
     abstra
    0.43
    geti
    0.43
     demeure
    0.42
    Activations Density 0.001%

    No Known Activations