© 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. 129276
    Prev
    Next
    INDEX
    Explanations

    adding or removing elements

    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
     Kirche
    -0.06
    embal
    -0.06
    rendo
    -0.06
    ்களில்
    -0.05
     veto
    -0.05
    屼
    -0.05
     wins
    -0.05
    afel
    -0.05
    一路
    -0.05
     SAFE
    -0.05
    POSITIVE LOGITS
     شاید
    0.07
     spesso
    0.06
     baths
    0.06
     समस्याओं
    0.06
     troubleshooting
    0.06
     няколко
    0.06
     talvez
    0.06
     স্য
    0.06
     хло
    0.06
     Troubleshooting
    0.06
    Activations Density 0.025%

    No Known Activations