© 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. 116463
    Prev
    Next
    INDEX
    Explanations

    PM times with numbers

    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
     یکی
    -0.07
    These
    -0.07
    nections
    -0.06
     রাস্তার
    -0.06
     втор
    -0.06
     последний
    -0.06
    这些
    -0.06
     这
    -0.06
     third
    -0.06
     these
    -0.06
    POSITIVE LOGITS
     predominant
    0.06
     later
    0.06
     এজেন্ট
    0.06
    fordert
    0.06
     cominc
    0.06
    NVIC
    0.06
     दुर्गेश
    0.06
     më
    0.06
     póź
    0.06
    PARSE
    0.05
    Activations Density 0.007%

    No Known Activations