© 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. 130374
    Prev
    Next
    INDEX
    Explanations

    $\sigma$ notation

    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
     -,
    -0.07
    ;'
    -0.06
     这
    -0.06
     일반적으로
    -0.06
     चमकदार
    -0.06
    मेर
    -0.06
     這
    -0.06
    asher
    -0.06
     porcent
    -0.06
    :,
    -0.06
    POSITIVE LOGITS
    を示す
    0.06
    ļu
    0.05
    insc
    0.05
     Leop
    0.05
    seeking
    0.05
     поперед
    0.05
     pew
    0.05
     expresión
    0.05
     appeal
    0.05
     Philosophie
    0.05
    Activations Density 0.002%

    No Known Activations