© 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. 119832
    Prev
    Next
    INDEX
    Explanations

    how or the way

    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
     using
    -0.07
    ၏
    -0.07
    istern
    -0.07
     accuracy
    -0.06
     expectation
    -0.06
     absent
    -0.06
    াঙ্গ
    -0.06
     vollständig
    -0.06
     ಸಂಪ
    -0.06
    ('#
    -0.06
    POSITIVE LOGITS
     any
    0.06
     APPROACH
    0.06
     अर्ज
    0.05
    approach
    0.05
    responseData
    0.05
     fruitful
    0.05
     disjoint
    0.05
    カテゴ
    0.05
     بڑ
    0.05
     そ
    0.05
    Activations Density 0.065%

    No Known Activations