© 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. 117362
    Prev
    Next
    INDEX
    Explanations

    permanent methods

    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
     συμμε
    -0.07
    egy
    -0.06
     تلف
    -0.06
     velič
    -0.06
    ｀)
    -0.06
    ovis
    -0.06
     waterfowl
    -0.06
     Stunden
    -0.06
    規模
    -0.05
     بزرگ
    -0.05
    POSITIVE LOGITS
     permanence
    0.12
     Perman
    0.12
     perman
    0.12
     permanently
    0.12
     permanent
    0.12
    Perman
    0.12
    perman
    0.12
    永久
    0.11
     Permanent
    0.11
    Permanent
    0.11
    Activations Density 0.083%

    No Known Activations