© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119784
    Prev
    Next
    INDEX
    Explanations

    confession or negative feeling

    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
     einzigen
    -0.08
    只有
    -0.07
     ONLY
    -0.06
     ಮತ್ತ
    -0.06
     informasi
    -0.06
     unless
    -0.06
    除非
    -0.06
     ekstrem
    -0.06
    ⬇
    -0.06
     doar
    -0.06
    POSITIVE LOGITS
    äus
    0.06
     vytvá
    0.06
     sounding
    0.06
     rupam
    0.06
     sbag
    0.05
     inadvertently
    0.05
     slidesToShow
    0.05
     appearing
    0.05
    চ্ছন্ন
    0.05
     getting
    0.05
    Activations Density 0.043%

    No Known Activations