© 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. 70468
    Prev
    Next
    INDEX
    Explanations

    taxes and billionaires

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

    promoting discrimination

    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
     イ
    0.50
     ક
    0.50
    А
    0.50
     エ
    0.47
    அ
    0.46
    藿
    0.46
    и
    0.46
    を使
    0.46
     タ
    0.45
    ャ
    0.45
    POSITIVE LOGITS
     وهنا
    0.44
    Mfg
    0.41
     хирур
    0.41
    ,_-
    0.40
     }}=\
    0.40
     ani
    0.39
    ឆ្នាំ
    0.39
     vorbei
    0.39
    ymbol
    0.39
     hanem
    0.38
    Activations Density 0.005%

    No Known Activations