© 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. 129718
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

    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
    offset
    -0.06
    ackel
    -0.06
     piccole
    -0.06
     ocho
    -0.06
     interesado
    -0.06
    現状
    -0.06
    inflate
    -0.06
     orig
    -0.05
    Musical
    -0.05
    ഭാ
    -0.05
    POSITIVE LOGITS
    В
    0.06
     изменения
    0.06
     hd
    0.06
     richly
    0.06
     السابق
    0.06
     Habits
    0.06
     mantan
    0.06
    zyna
    0.06
    เนื้อ
    0.06
     غالب
    0.06
    Activations Density 0.028%

    No Known Activations