© 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. 128865
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ༺
    -0.06
    ostante
    -0.06
    some
    -0.06
    without
    -0.06
    😁
    -0.06
     zest
    -0.06
     весьма
    -0.05
    open
    -0.05
     કેટલાક
    -0.05
     довольно
    -0.05
    POSITIVE LOGITS
     প্রতিদিন
    0.06
     forming
    0.06
     appointed
    0.06
     लड़के
    0.06
     are
    0.06
     স্বাধীনতা
    0.06
     इन
    0.06
     bereits
    0.06
     transcripts
    0.06
     inspections
    0.06
    Activations Density 0.005%

    No Known Activations