© 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. 208936
    Prev
    Next
    INDEX
    Explanations

    days from time

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

    foreign characters and principles

    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
    uların
    0.54
    ুনিক
    0.52
    з
    0.52
    л
    0.52
     kullanıcı
    0.51
     pestaña
    0.51
    น้อง
    0.50
    дак
    0.50
     animasi
    0.50
     regarde
    0.50
    POSITIVE LOGITS
     Principles
    0.43
    Conv
    0.42
    Principles
    0.42
    grund
    0.41
     লন্ড
    0.41
    PLC
    0.41
    衡
    0.39
    PES
    0.39
     egot
    0.39
    odot
    0.38
    Activations Density 0.000%

    No Known Activations