© 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. 129347
    Prev
    Next
    INDEX
    Explanations

    alpha alpha(2) agonist

    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
     several
    -0.06
    娛樂
    -0.06
     উক্ত
    -0.06
    াপ্র
    -0.06
     بڑا
    -0.06
    娱乐
    -0.06
     continuer
    -0.06
     repertoire
    -0.06
    ewomen
    -0.06
    ﾟ
    -0.06
    POSITIVE LOGITS
     tatu
    0.07
     outskirts
    0.06
     insc
    0.06
     গর্ব
    0.06
     meticulous
    0.06
    леку
    0.06
    തീ
    0.06
    scaled
    0.06
     nanos
    0.06
     ascetic
    0.06
    Activations Density 0.003%

    No Known Activations