© 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. 130157
    Prev
    Next
    INDEX
    Explanations

    Hoboken

    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
     svůj
    -0.07
    /]
    -0.06
     werden
    -0.06
    Using
    -0.06
     gewinnen
    -0.06
     используются
    -0.06
    意识
    -0.06
     for
    -0.06
     abordagem
    -0.06
    意識
    -0.06
    POSITIVE LOGITS
     більше
    0.06
     म्हणजे
    0.05
    ใหม่
    0.05
     विश्वास
    0.05
     Andrey
    0.05
    ICY
    0.05
     específ
    0.05
     মর্ম
    0.05
    เอียด
    0.05
     –
    0.05
    Activations Density 0.001%

    No Known Activations