© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116360
    Prev
    Next
    INDEX
    Explanations

    cellular telephones or communications

    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
     нужна
    -0.07
     እንደሚ
    -0.07
     roja
    -0.06
    रीय
    -0.06
    olda
    -0.06
     पासवर्ड
    -0.06
    她们
    -0.06
     每
    -0.06
     biología
    -0.06
     ら
    -0.06
    POSITIVE LOGITS
     which
    0.08
     consecutively
    0.07
     DMA
    0.06
    which
    0.06
     successively
    0.06
     इन्हीं
    0.06
     radiations
    0.06
    inness
    0.06
     
    0.06
    庄
    0.05
    Activations Density 0.033%

    No Known Activations