© 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. 120575
    Prev
    Next
    INDEX
    Explanations

    places after "from"

    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
     menghad
    -0.06
     Rug
    -0.06
    che
    -0.05
     Chees
    -0.05
    Besides
    -0.05
    。
    -0.05
    大多
    -0.05
     nyil
    -0.05
     বল
    -0.05
    年至
    -0.05
    POSITIVE LOGITS
    ↓
    0.07
     decidió
    0.06
     сможет
    0.06
     установки
    0.06
     aforementioned
    0.06
    ूर्त
    0.06
     способен
    0.06
    데일리
    0.06
    FuncName
    0.06
     citoyens
    0.06
    Activations Density 0.005%

    No Known Activations