© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120343
    Prev
    Next
    INDEX
    Explanations

    "a five"

    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
    ِن
    -0.06
     μόνο
    -0.06
     такими
    -0.06
     চলা
    -0.06
     официально
    -0.06
     Memorandum
    -0.06
    三分
    -0.06
    完璧
    -0.05
    既に
    -0.05
    aily
    -0.05
    POSITIVE LOGITS
     শিক্ষার্থীরা
    0.07
     डिफेंस
    0.06
     Africa
    0.06
    리오
    0.06
    related
    0.06
     Partners
    0.06
     orice
    0.05
    ito
    0.05
    urches
    0.05
    teams
    0.05
    Activations Density 0.021%

    No Known Activations