© 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. 179681
    Prev
    Next
    INDEX
    Explanations

    and more!

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

    ethical principles

    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
    говор
    0.49
    W
    0.48
    Tower
    0.46
     rodents
    0.44
    жливо
    0.43
    Touched
    0.42
    Hunter
    0.42
    Steel
    0.42
    V
    0.42
     for
    0.41
    POSITIVE LOGITS
    akkha
    0.57
    🕝
    0.51
     måde
    0.49
    efeuille
    0.49
    ,_
    0.48
    সম্যান
    0.48
     SrvGroup
    0.48
    =[]
    0.48
    igheten
    0.47
    🕤
    0.47
    Activations Density 0.001%

    No Known Activations