© 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. 129083
    Prev
    Next
    INDEX
    Explanations

    park or community organization

    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
     rappel
    -0.06
     targeting
    -0.06
     위험
    -0.06
    ől
    -0.06
     버전
    -0.06
     ஏற்படுத்த
    -0.06
     version
    -0.06
     spanned
    -0.06
     nerveux
    -0.06
     on
    -0.06
    POSITIVE LOGITS
     insisted
    0.07
     UNESCO
    0.06
     opin
    0.06
     prestigious
    0.06
    作为
    0.06
     botched
    0.06
     prestige
    0.06
    prest
    0.06
     Have
    0.06
     prestig
    0.06
    Activations Density 0.043%

    No Known Activations