© 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. 197898
    Prev
    Next
    INDEX
    Explanations

    booking, impossible, possible, physicians

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

    law, injustice, professions, work, needs

    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
     ress
    0.46
     cht
    0.45
    ccncc
    0.43
    mbox
    0.43
     tes
    0.42
     castor
    0.42
    plib
    0.41
    ↵
    0.41
     fontos
    0.41
     dirig
    0.40
    POSITIVE LOGITS
     ashore
    0.49
     журнали
    0.43
    游戏中
    0.43
    战场
    0.43
     rumoured
    0.42
    渟
    0.42
    Wear
    0.42
     लापर
    0.41
     विदेश
    0.41
    гон
    0.41
    Activations Density 0.003%

    No Known Activations