© 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. 106616
    Prev
    Next
    INDEX
    Explanations

    First Lieutenant stories

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

    right, but not the obligation

    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
    年中
    0.46
     تعالی
    0.46
    그러
    0.46
    criptors
    0.44
    笺
    0.44
    FindAsync
    0.44
     Honorary
    0.44
    StaticHandler
    0.43
    اندی
    0.42
     头
    0.42
    POSITIVE LOGITS
    vem
    0.49
    immune
    0.45
     forn
    0.44
    नमस्ते
    0.44
     לנ
    0.43
     कब
    0.43
     দুর্নীতি
    0.42
    kind
    0.42
     Vem
    0.42
    奢侈
    0.41
    Activations Density 0.001%

    No Known Activations