© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130918
    Prev
    Next
    INDEX
    Explanations

    email subjects or headers

    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
     mellan
    -0.08
     tussen
    -0.08
     까지
    -0.07
     між
    -0.07
     ಒಳ್ಳೆಯ
    -0.07
     ________
    -0.07
    良い
    -0.06
     между
    -0.06
     dicen
    -0.06
     avoid
    -0.06
    POSITIVE LOGITS
    Some
    0.06
     (
    0.06
     includes
    0.06
    ដែលអាច
    0.06
     graciously
    0.06
     and
    0.05
     FACT
    0.05
    采用了
    0.05
    Universität
    0.05
    包括
    0.05
    Activations Density 0.001%

    No Known Activations