© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130873
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states of mind

    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
     ज्ये
    -0.06
    तीत
    -0.06
    -)
    -0.06
     तबीयत
    -0.06
    ↵
    -0.05
    㱛
    -0.05
     gdyż
    -0.05
    პი
    -0.05
    nání
    -0.05
    Court
    -0.05
    POSITIVE LOGITS
     разными
    0.07
    हिर
    0.06
    ､
    0.06
     다양한
    0.06
     _
    0.06
     suitable
    0.06
     различными
    0.06
     différentes
    0.06
     eller
    0.06
     different
    0.06
    Activations Density 0.030%

    No Known Activations