© 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. 130552
    Prev
    Next
    INDEX
    Explanations

    SEC website and links

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

    vary or frequency

    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
    ↵
    0.47
     মিলিয়ে
    0.45
    amard
    0.43
     Бе
    0.42
    gcj
    0.42
     అర్జు
    0.41
     খেজুর
    0.40
     prelude
    0.40
     చో
    0.40
     вопросам
    0.40
    POSITIVE LOGITS
     établ
    0.57
    認為
    0.57
     biologique
    0.54
    认为
    0.48
    o
    0.47
    证券
    0.46
    iii
    0.45
     setCart
    0.45
    oooo
    0.45
     établi
    0.44
    Activations Density 0.001%

    No Known Activations