© 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. 129262
    Prev
    Next
    INDEX
    Explanations

    results and findings

    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
     hundreds
    -0.07
     waarde
    -0.06
     scores
    -0.06
    checkFor
    -0.06
     América
    -0.06
     ESPN
    -0.06
     utilisez
    -0.06
    achute
    -0.06
     après
    -0.06
     equilibrated
    -0.06
    POSITIVE LOGITS
    第二个
    0.06
    Str
    0.06
    ate
    0.06
    Way
    0.06
     
    0.05
    St
    0.05
    Stage
    0.05
    她说
    0.05
    En
    0.05
    An
    0.05
    Activations Density 0.031%

    No Known Activations