© 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. 129427
    Prev
    Next
    INDEX
    Explanations

    technical contexts and notifications

    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
    其它
    -0.07
     innych
    -0.07
     other
    -0.06
    Other
    -0.06
     forti
    -0.06
     많은
    -0.06
     günlük
    -0.06
     otros
    -0.06
    ség
    -0.06
     சேர்த்த
    -0.06
    POSITIVE LOGITS
    robespierre
    0.06
     reboot
    0.06
     voltage
    0.06
     geplant
    0.06
     november
    0.06
    のお知らせ
    0.06
     preparando
    0.06
     intranet
    0.06
     noticed
    0.06
     planned
    0.06
    Activations Density 0.003%

    No Known Activations