© 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. 118620
    Prev
    Next
    INDEX
    Explanations

    quality and company

    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
    人材
    -0.07
    উপর
    -0.06
     unconventional
    -0.06
     quirky
    -0.06
     каждого
    -0.06
     examined
    -0.06
    southeast
    -0.06
    Toolset
    -0.06
    แต่ละ
    -0.06
     지역
    -0.06
    POSITIVE LOGITS
    यास
    0.07
    真正
    0.06
     sustained
    0.06
     or
    0.06
    AK
    0.05
    моби
    0.05
     რუს
    0.05
    russ
    0.05
     Ihrer
    0.05
    KK
    0.05
    Activations Density 0.063%

    No Known Activations