© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117871
    Prev
    Next
    INDEX
    Explanations

    types of, relatively short, assembly line

    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
     always
    -0.06
     really
    -0.06
     based
    -0.06
     nagging
    -0.06
     format
    -0.06
     weird
    -0.06
     avoids
    -0.06
    োরের
    -0.06
     strangely
    -0.06
     avoiding
    -0.06
    POSITIVE LOGITS
     مصنوعی
    0.06
    指示
    0.06
     Clarkson
    0.06
    펌
    0.06
     행동
    0.06
     Хабаровского
    0.05
    貴重
    0.05
     대
    0.05
     aprob
    0.05
     will
    0.05
    Activations Density 0.030%

    No Known Activations