© 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-16K
    7. 12854
    Prev
    Next
    INDEX
    Explanations

    specific word beginnings and following words

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

    initial words in common phrases

    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_16k_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
    ன்
    0.92
    л
    0.91
    ن
    0.88
     for
    0.82
    st
    0.73
    simile
    0.71
     فريبي
    0.70
    د
    0.68
     offerte
    0.66
    스는
    0.66
    POSITIVE LOGITS
     a
    1.05
    {
    0.92
    1
    0.90
    다
    0.82
    ا
    0.78
    ா
    0.77
    ా
    0.74
    いますが
    0.73
    도
    0.68
    ंका
    0.67
    Activations Density 5.467%

    No Known Activations