© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118058
    Prev
    Next
    INDEX
    Explanations

    **calibrating reference standards**

    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
    이지만
    -0.06
     শতাংশ
    -0.06
    يًا
    -0.06
    羚
    -0.06
     अज्ञात
    -0.06
    éral
    -0.05
     calmer
    -0.05
     hyvä
    -0.05
    inoff
    -0.05
     Kand
    -0.05
    POSITIVE LOGITS
     most
    0.06
     volle
    0.06
    ଏ
    0.06
     shows
    0.06
     नयी
    0.06
    电商
    0.06
     leach
    0.06
     solic
    0.06
     Most
    0.06
    AttrName
    0.06
    Activations Density 0.006%

    No Known Activations