© 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. 129783
    Prev
    Next
    INDEX
    Explanations

    string, DB, group, 2

    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
    場面
    -0.06
     मंत्रियों
    -0.06
     combined
    -0.06
     diminished
    -0.05
     diminish
    -0.05
     intruders
    -0.05
     intruder
    -0.05
    回避
    -0.05
    afin
    -0.05
     combinado
    -0.05
    POSITIVE LOGITS
     Similarly
    0.07
     ober
    0.07
     സ്വന്ത
    0.07
     wenn
    0.07
    Similarly
    0.06
     propria
    0.06
    明确
    0.06
     but
    0.06
     если
    0.06
     zase
    0.06
    Activations Density 0.005%

    No Known Activations