© 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. 119614
    Prev
    Next
    INDEX
    Explanations

    branching, jumping, indirect calls, enhancement, cartoon violence

    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
    दर्द
    -0.07
     trabajando
    -0.07
     distress
    -0.06
     درد
    -0.06
     வைர
    -0.06
     Patrice
    -0.06
    痛苦
    -0.06
     জন্য
    -0.06
     கிடைக்கும்
    -0.06
     clientèle
    -0.06
    POSITIVE LOGITS
    carbon
    0.06
     verified
    0.06
    olf
    0.06
    ปัจ
    0.06
     ስርዓ
    0.06
    vision
    0.06
     سالم
    0.06
     verificación
    0.06
     vision
    0.06
     অত্য
    0.06
    Activations Density 0.001%

    No Known Activations