© 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. 120125
    Prev
    Next
    INDEX
    Explanations

    offensive 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
     उद्देश्यों
    -0.07
     что
    -0.06
     children
    -0.06
     மனு
    -0.06
     notwend
    -0.06
     hoặc
    -0.06
    onc
    -0.06
    पूर्ति
    -0.06
     geist
    -0.06
    이가
    -0.06
    POSITIVE LOGITS
    凭
    0.06
     WHEN
    0.06
     brillante
    0.06
    WHEN
    0.06
     грамо
    0.06
    的好
    0.05
    फॉर्म
    0.05
     excepting
    0.05
     brillantes
    0.05
     dB
    0.05
    Activations Density 0.002%

    No Known Activations