© 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. 119204
    Prev
    Next
    INDEX
    Explanations

    android schemas tools attributes

    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
    ജീ
    -0.06
     அம்ச
    -0.06
     esenciales
    -0.06
    mma
    -0.06
     generales
    -0.06
     manne
    -0.06
    功能的
    -0.06
     iniciativas
    -0.06
    機能を
    -0.06
     パール
    -0.06
    POSITIVE LOGITS
     =>
    0.06
    扱
    0.06
     goes
    0.06
     territ
    0.06
     supremely
    0.06
     heartache
    0.05
     heartbreak
    0.05
    rator
    0.05
     airplane
    0.05
    antiago
    0.05
    Activations Density 0.001%

    No Known Activations