© 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. 128985
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    悪い
    -0.07
     attributes
    -0.07
     Abstract
    -0.06
     χωρίς
    -0.06
    aghetti
    -0.06
     tedious
    -0.06
     পাপ
    -0.06
    jeh
    -0.06
     DOI
    -0.06
     tanpa
    -0.06
    POSITIVE LOGITS
     luxury
    0.07
    \,
    0.06
    食べ
    0.05
     occupant
    0.05
    ंत्र
    0.05
     extraordin
    0.05
     丨
    0.05
    Luxury
    0.05
     lanzado
    0.05
     введен
    0.05
    Activations Density 0.002%

    No Known Activations