© 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. 117228
    Prev
    Next
    INDEX
    Explanations

    localization

    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
     त्यानुसार
    -0.07
     suffoc
    -0.06
    :
    -0.06
     प्रोफेसर
    -0.06
    стов
    -0.06
    你
    -0.06
    하지만
    -0.06
    они
    -0.06
    JButton
    -0.06
     давления
    -0.06
    POSITIVE LOGITS
    heure
    0.07
     heure
    0.06
    のみ
    0.06
     ért
    0.05
     제외
    0.05
    は何
    0.05
     ive
    0.05
     сете
    0.05
     समेत
    0.05
    肴
    0.05
    Activations Density 0.003%

    No Known Activations