© 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. 95574
    Prev
    Next
    INDEX
    Explanations

    contract, markets, insufficient, first, application, accordance, indemnify

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

    Berghain, climate, ETH, search

    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
     land
    0.50
     deles
    0.49
     oldCount
    0.48
     entityManager
    0.46
     tills
    0.46
     두
    0.46
     alley
    0.46
     올려
    0.44
     κι
    0.43
     golden
    0.43
    POSITIVE LOGITS
    তিরিক্ত
    0.49
    গ্রহণ
    0.47
     Jail
    0.47
    ͍
    0.46
    Ə
    0.45
    Although
    0.45
    EVER
    0.44
    Интернет
    0.44
    原因
    0.44
    Zur
    0.44
    Activations Density 0.001%

    No Known Activations