© 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. 119151
    Prev
    Next
    INDEX
    Explanations

    ways to make

    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
    It
    -0.06
    Should
    -0.06
    他
    -0.06
    But
    -0.06
    但
    -0.06
    ையாள
    -0.06
    should
    -0.06
    Generally
    -0.05
    Bret
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    如此
    0.06
     weitere
    0.06
     kadar
    0.06
     такую
    0.06
     of
    0.06
     další
    0.06
     तापमान
    0.06
    こんな
    0.06
     ulteriori
    0.06
     rağmen
    0.06
    Activations Density 0.007%

    No Known Activations