© 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. 129997
    Prev
    Next
    INDEX
    Explanations

    form-horizontal layout or structure

    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
     jarang
    -0.06
     כל
    -0.06
     combinación
    -0.06
    行き
    -0.06
    一个人
    -0.05
     неожидан
    -0.05
     செய
    -0.05
     shocking
    -0.05
    ado
    -0.05
    лда
    -0.05
    POSITIVE LOGITS
     Anastasia
    0.06
    starts
    0.06
     begyn
    0.06
    вшиеся
    0.06
     তারা
    0.06
     elapsedTime
    0.06
     있죠
    0.06
    Starts
    0.06
    <0xBF>
    0.06
    asic
    0.06
    Activations Density 0.001%

    No Known Activations