© 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. 119148
    Prev
    Next
    INDEX
    Explanations

    business listings

    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
     from
    -0.06
     pumpkins
    -0.06
    ایید
    -0.06
     From
    -0.06
    留学
    -0.06
     лета
    -0.06
    入境
    -0.06
     যেকোনো
    -0.06
     Examinations
    -0.05
     procédure
    -0.05
    POSITIVE LOGITS
    directory
    0.07
     services
    0.07
     utility
    0.07
     directory
    0.06
     servicios
    0.06
    ธุรกิจ
    0.06
     coated
    0.06
     Биз
    0.06
     serviços
    0.06
     dechlor
    0.06
    Activations Density 0.004%

    No Known Activations