© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129975
    Prev
    Next
    INDEX
    Explanations

    a string of numbers and words

    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
     amigo
    -0.07
     أوروب
    -0.06
     생각
    -0.06
    斃
    -0.06
     sophistic
    -0.06
    lingu
    -0.06
     ফোনের
    -0.06
    学院
    -0.06
     amico
    -0.06
    Depth
    -0.06
    POSITIVE LOGITS
    了大
    0.06
     partout
    0.06
     大
    0.06
     ihn
    0.06
    ിക്കുന്നു
    0.06
    しておく
    0.06
     بتا
    0.05
    সঙ্ঘ
    0.05
     সেই
    0.05
    。
    0.05
    Activations Density 0.009%

    No Known Activations