© 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. 119184
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
    도
    -0.07
    uların
    -0.07
     hitherto
    -0.06
    も
    -0.06
     अभिनंदन
    -0.06
     कक्कड़
    -0.06
     இருப்பதாக
    -0.06
     pakai
    -0.06
    ज्योति
    -0.06
    ussi
    -0.06
    POSITIVE LOGITS
     it
    0.07
    instit
    0.06
     institut
    0.06
    適切な
    0.05
    ;.
    0.05
    自行
    0.05
     خواهند
    0.05
    ('
    0.05
     данный
    0.05
     massages
    0.05
    Activations Density 0.015%

    No Known Activations