© 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. 120484
    Prev
    Next
    INDEX
    Explanations

    microchip number; details

    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
     mwaka
    -0.06
    今年も
    -0.06
    Adjacent
    -0.06
    like
    -0.06
    今年は
    -0.06
    Multicolored
    -0.06
     நிறைந்த
    -0.06
     سنه
    -0.06
     tahun
    -0.05
     दाब
    -0.05
    POSITIVE LOGITS
     if
    0.07
     desperation
    0.07
    如果
    0.07
     kindness
    0.07
    图书
    0.06
     如果
    0.06
     પ્રથમ
    0.06
    khidmat
    0.06
    緊急
    0.06
     calling
    0.06
    Activations Density 0.003%

    No Known Activations