© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130842
    Prev
    Next
    INDEX
    Explanations

    body parts and related items

    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
    Poor
    -0.07
    開き
    -0.06
     હતી
    -0.06
     समझेंगे
    -0.06
     फोटोशूट
    -0.06
     ہے
    -0.06
     vérifier
    -0.06
     دوران
    -0.06
    检查
    -0.06
     observed
    -0.06
    POSITIVE LOGITS
     olymp
    0.06
     human
    0.06
     разум
    0.06
    Alc
    0.05
     mastermind
    0.05
     ndi
    0.05
     Our
    0.05
    门
    0.05
     ni
    0.05
     தேர்த
    0.05
    Activations Density 0.022%

    No Known Activations