© 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. 116853
    Prev
    Next
    INDEX
    Explanations

    bodies of water

    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
     complications
    -0.07
    ສໍາ
    -0.06
    dbname
    -0.06
    saves
    -0.05
     tablespoons
    -0.05
     statewide
    -0.05
     throwback
    -0.05
     خواتین
    -0.05
     Vintage
    -0.05
     उर्फी
    -0.05
    POSITIVE LOGITS
     which
    0.08
     koje
    0.06
     Which
    0.06
    期間限定
    0.06
     뭘
    0.06
     Films
    0.06
     घेऊन
    0.06
     често
    0.06
     pensée
    0.06
     située
    0.06
    Activations Density 0.011%

    No Known Activations