© 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. 118796
    Prev
    Next
    INDEX
    Explanations

    feeling pain or sadness

    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
    τική
    -0.07
    attractive
    -0.07
     لكن
    -0.06
     sejak
    -0.06
    because
    -0.06
     attractive
    -0.06
     دوسروں
    -0.06
    সম্মত
    -0.06
     BECAUSE
    -0.06
     ballistic
    -0.06
    POSITIVE LOGITS
     into
    0.07
    성에
    0.06
     chance
    0.06
     ihrer
    0.06
    :)
    0.06
     wildflowers
    0.05
     doctors
    0.05
    SError
    0.05
     অভিম
    0.05
    iculture
    0.05
    Activations Density 0.022%

    No Known Activations