© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116204
    Prev
    Next
    INDEX
    Explanations

    military and historical events

    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
     all
    -0.07
     would
    -0.06
    <h2>
    -0.06
    <h3>
    -0.06
    ten
    -0.06
    高
    -0.06
    <h1>
    -0.06
    عل
    -0.05
     высоко
    -0.05
     sampel
    -0.05
    POSITIVE LOGITS
    Middleware
    0.07
    کسی
    0.07
     screenshots
    0.07
     berhasil
    0.06
     Pakistan
    0.06
    殲
    0.06
     mendapatkan
    0.06
     Docker
    0.06
    stagram
    0.06
    atisf
    0.06
    Activations Density 0.001%

    No Known Activations