© 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. 212678
    Prev
    Next
    INDEX
    Explanations

    owned and controlled by

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

    AI explaining user intent

    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
    дал
    0.55
     পাকিস্তানীদের
    0.52
     সম্পূর্ন
    0.51
    তাহাদের
    0.50
    ोतरी
    0.49
    λον
    0.49
    бан
    0.48
    𝐍
    0.48
    海军
    0.47
    onnage
    0.47
    POSITIVE LOGITS
     durante
    0.52
     liters
    0.52
     deaktiv
    0.52
     worsen
    0.51
     maniac
    0.50
     tokom
    0.49
     craz
    0.49
     unwanted
    0.49
     عادة
    0.48
     wart
    0.48
    Activations Density 0.000%

    No Known Activations