© 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. 120459
    Prev
    Next
    INDEX
    Explanations

    "Four", "Ar", "A", "Miss"

    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
     na
    -0.06
     gute
    -0.06
     পাখ
    -0.06
     이걸
    -0.06
     by
    -0.06
     আসল
    -0.05
     сказал
    -0.05
     อาจ
    -0.05
    也很
    -0.05
     nisso
    -0.05
    POSITIVE LOGITS
     typically
    0.07
     eigenlijk
    0.07
     underpinned
    0.07
    typically
    0.07
     एकूण
    0.06
     newly
    0.06
     workflow
    0.06
    Typically
    0.06
     系统
    0.06
     telephony
    0.06
    Activations Density 0.002%

    No Known Activations