© 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. 138283
    Prev
    Next
    INDEX
    Explanations

    social change, proposed facility, biophysical profile

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

    Yes!

    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
    anon
    0.48
    adress
    0.48
    o
    0.47
    escaping
    0.45
    altura
    0.44
     Cuthbert
    0.43
    piry
    0.43
    udon
    0.43
    activation
    0.43
     ကု
    0.42
    POSITIVE LOGITS
    Builders
    0.51
    द्धांत
    0.48
    Agricult
    0.47
     Slavic
    0.46
    লের
    0.46
     যেটি
    0.46
    ologischen
    0.45
    흡
    0.45
     overeen
    0.44
     pick
    0.44
    Activations Density 0.002%

    No Known Activations