© 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. 169055
    Prev
    Next
    INDEX
    Explanations

    legal liability and claims

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

    `>` command, managing, range

    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
    Amb
    0.47
    ick
    0.45
    菀
    0.45
    ρό
    0.44
    壑
    0.44
     स्रोत
    0.44
     اتر
    0.44
    ट्टे
    0.43
    Tom
    0.43
    傑
    0.43
    POSITIVE LOGITS
     Nicaragua
    0.50
     Prz
    0.48
     coriander
    0.48
    মানা
    0.47
     lizard
    0.46
     Zambia
    0.46
     Moringa
    0.46
     infantil
    0.46
     chili
    0.45
    "*
    0.45
    Activations Density 0.001%

    No Known Activations