© 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. 119361
    Prev
    Next
    INDEX
    Explanations

    Asian women

    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
    ALL
    -0.06
     hiç
    -0.06
     viaje
    -0.06
    amnă
    -0.06
    গন্ধ
    -0.05
    Mapping
    -0.05
    Among
    -0.05
    among
    -0.05
    Part
    -0.05
    hence
    -0.05
    POSITIVE LOGITS
     if
    0.08
     can
    0.08
     rhetoric
    0.07
     secondly
    0.06
    .$(
    0.06
     at
    0.06
     as
    0.06
     magnifique
    0.06
    如果
    0.06
     will
    0.06
    Activations Density 0.002%

    No Known Activations