© 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. 120687
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
     kiezen
    -0.07
     निरंतर
    -0.07
    每次
    -0.06
     seventy
    -0.06
    を選
    -0.06
     choosing
    -0.06
     chọn
    -0.06
    不管
    -0.06
     thirty
    -0.06
     пості
    -0.06
    POSITIVE LOGITS
     internal
    0.07
     প্রাথম
    0.06
     내부
    0.06
     grows
    0.06
     will
    0.06
     kapsamında
    0.06
     pembuatan
    0.06
     внутрен
    0.06
    wide
    0.06
    Internal
    0.06
    Activations Density 0.002%

    No Known Activations