© 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. 3779
    Prev
    Next
    INDEX
    Explanations

    product, service, or location

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

    introductions or specific topics

    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
     خارجه
    0.33
     প্রভৃতির
    0.31
    ActivityResult
    0.29
    }(
    0.28
     ஆரம்பித்த
    0.28
    ITARY
    0.27
     করিয়াছিল
    0.27
     moeilijk
    0.27
     salarié
    0.26
    ುಂಬ
    0.26
    POSITIVE LOGITS
    ！
    0.49
     для
    0.46
     Featuring
    0.45
    !
    0.45
     🎉
    0.45
    🤩
    0.44
     featuring
    0.44
     입니다
    0.42
     మీకు
    0.42
    ‼️
    0.41
    Activations Density 0.479%

    No Known Activations