© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129768
    Prev
    Next
    INDEX
    Explanations

    ifndef `#define`

    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
    യിരുന്നു
    -0.06
     fiercely
    -0.06
     कुंडली
    -0.06
    нах
    -0.06
     разум
    -0.06
    uni
    -0.06
     gigantic
    -0.05
    顾客
    -0.05
     மருத்து
    -0.05
    രു
    -0.05
    POSITIVE LOGITS
     wollen
    0.06
     modified
    0.06
     acquies
    0.06
    beitung
    0.06
    ையா
    0.06
     of
    0.06
    的高
    0.06
    とはいえ
    0.06
     restricciones
    0.06
    च्चय
    0.06
    Activations Density 0.001%

    No Known Activations