© 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. 128291
    Prev
    Next
    INDEX
    Explanations

    crystallography, polymorphism, moisture

    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
     jett
    -0.06
     pula
    -0.06
    custom
    -0.06
    買い物
    -0.06
    addNew
    -0.06
    成为
    -0.06
     touche
    -0.05
     "-",
    -0.05
    യാ
    -0.05
    cq
    -0.05
    POSITIVE LOGITS
     welchen
    0.06
     ভারতকে
    0.06
     hlavní
    0.06
     absen
    0.06
    mites
    0.06
     punctual
    0.06
     timing
    0.06
     Time
    0.06
     ভ্যাকসিন
    0.06
    用心
    0.06
    Activations Density 0.002%

    No Known Activations