© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14173
    Prev
    Next
    INDEX
    Explanations

    return false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ắt
    0.50
    о
    0.39
    ור
    0.39
    런
    0.39
    鎳
    0.38
    Ни
    0.38
    Tecla
    0.38
    ใ
    0.36
    Три
    0.36
    てる
    0.36
    POSITIVE LOGITS
     and
    0.42
     ja
    0.41
     with
    0.40
     transaksi
    0.40
     (
    0.39
     salaried
    0.39
     przy
    0.39
     prosecutors
    0.39
     when
    0.38
     accompanied
    0.38
    Activations Density 0.099%

    No Known Activations