© 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. 130641
    Prev
    Next
    INDEX
    Explanations

    FirstLight Home Care

    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
    läufig
    -0.06
    此
    -0.06
     Colegio
    -0.06
    नाच्या
    -0.06
    ffffff
    -0.06
     afgelopen
    -0.06
     Dubey
    -0.06
     нами
    -0.06
     ГО
    -0.06
     culmin
    -0.06
    POSITIVE LOGITS
     खड़े
    0.06
     posee
    0.06
     крю
    0.06
    也能
    0.06
     também
    0.06
     개선
    0.06
    வதில்
    0.05
     también
    0.05
     Shores
    0.05
    )،
    0.05
    Activations Density 0.001%

    No Known Activations