© 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. 128435
    Prev
    Next
    INDEX
    Explanations

    mercenary and specific names

    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
     CRISPR
    -0.07
     unprecedented
    -0.07
    🐭
    -0.06
    🌑
    -0.06
     অনিশ্চ
    -0.06
     ;-
    -0.06
    enabled
    -0.06
     Brookings
    -0.06
     Huffington
    -0.06
    哄
    -0.06
    POSITIVE LOGITS
     filming
    0.07
    BI
    0.07
     some
    0.07
     designated
    0.07
     काही
    0.06
     някои
    0.06
     ধর্ষণের
    0.06
     على
    0.06
     presumably
    0.06
     специальных
    0.06
    Activations Density 0.008%

    No Known Activations