© 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. 129965
    Prev
    Next
    INDEX
    Explanations

    reference markers

    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
    延续
    -0.06
    ě
    -0.06
     establishing
    -0.05
     ecc
    -0.05
    َم
    -0.05
    +
    -0.05
    erre
    -0.05
    的长
    -0.05
     alebo
    -0.05
    plemented
    -0.05
    POSITIVE LOGITS
    それを
    0.07
     новую
    0.06
     metastasis
    0.06
     référence
    0.06
     одну
    0.06
    它们
    0.06
    ികളെ
    0.06
     padassa
    0.06
     proficiency
    0.06
     μετά
    0.06
    Activations Density 0.003%

    No Known Activations