© 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. 130623
    Prev
    Next
    INDEX
    Explanations

    testing or annotations

    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
    false
    -0.06
    ?,
    -0.06
     for
    -0.06
     false
    -0.05
    approx
    -0.05
     falsely
    -0.05
    單位
    -0.05
     hoofd
    -0.05
     कर्मचारियों
    -0.05
     $:=$
    -0.05
    POSITIVE LOGITS
     durchgeführt
    0.08
    先前
    0.07
     после
    0.07
     conducted
    0.07
    前提
    0.07
     außen
    0.07
     Voraussetzungen
    0.07
     aspetti
    0.07
     después
    0.07
     envision
    0.07
    Activations Density 0.009%

    No Known Activations