© 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. 119061
    Prev
    Next
    INDEX
    Explanations

    abusive language and attacks

    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
    最为
    -0.07
     of
    -0.07
     löyty
    -0.06
     ઓફ
    -0.06
     både
    -0.06
    Various
    -0.06
     aflat
    -0.06
    阻
    -0.06
     zowel
    -0.06
     seemingly
    -0.06
    POSITIVE LOGITS
     return
    0.06
     endogenous
    0.06
     recent
    0.06
    人了
    0.06
     Sénégal
    0.06
    ǎ
    0.06
     ትንሽ
    0.06
     lentement
    0.06
     stades
    0.06
     gardening
    0.06
    Activations Density 0.002%

    No Known Activations