© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116386
    Prev
    Next
    INDEX
    Explanations

    records, field, detailed, successful descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     can
    -0.06
    -0.06
    改为
    -0.05
     المتح
    -0.05
    واز
    -0.05
     changed
    -0.05
     മുതല്‍
    -0.05
     ঘটে
    -0.05
     automatis
    -0.05
    ቻል
    -0.05
    POSITIVE LOGITS
    塑料
    0.07
     consummate
    0.07
     vignette
    0.06
    عبد
    0.06
     señal
    0.06
     വിശദ
    0.06
    まさに
    0.06
     отлично
    0.06
     Với
    0.06
     Unidad
    0.06
    Activations Density 0.005%

    No Known Activations