© 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. 128714
    Prev
    Next
    INDEX
    Explanations

    origin=

    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
    నాన్ని
    -0.07
    ও
    -0.06
    িরা
    -0.06
     zum
    -0.06
    手里
    -0.06
    ndes
    -0.06
     अंतिम
    -0.06
     वर्तमान
    -0.06
     আদর
    -0.06
     nieuwe
    -0.06
    POSITIVE LOGITS
     وكذلك
    0.08
     sowie
    0.07
     serta
    0.07
     以及
    0.06
     penis
    0.06
    哃
    0.06
    besondere
    0.06
     Penis
    0.06
    easily
    0.06
     childish
    0.06
    Activations Density 0.001%

    No Known Activations