© 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. 129089
    Prev
    Next
    INDEX
    Explanations

    rumor or rumours

    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
     superficially
    -0.06
     سه
    -0.06
     dış
    -0.06
     situ
    -0.06
    Przy
    -0.06
    ategor
    -0.06
    रिक्
    -0.06
    标
    -0.06
     preferring
    -0.05
     যেদিন
    -0.05
    POSITIVE LOGITS
     rumor
    0.07
     rumored
    0.06
     semesters
    0.06
     rumores
    0.06
     rumour
    0.06
     πάντα
    0.06
     deven
    0.06
    噂
    0.06
    newL
    0.06
     sí
    0.06
    Activations Density 0.023%

    No Known Activations