© 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. 116413
    Prev
    Next
    INDEX
    Explanations

    expression or formula

    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
     obič
    -0.07
     dítě
    -0.06
     investigation
    -0.06
     ребён
    -0.06
    以前
    -0.06
     osserv
    -0.06
     கடந்த
    -0.06
    filtering
    -0.06
     gyerek
    -0.06
     alteration
    -0.06
    POSITIVE LOGITS
     Served
    0.06
    }.$$
    0.06
    cccc
    0.06
    ℉
    0.06
     intricacies
    0.05
    留下
    0.05
    ukh
    0.05
    堹
    0.05
     Cappadocia
    0.05
    しく
    0.05
    Activations Density 0.005%

    No Known Activations