© 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. 128830
    Prev
    Next
    INDEX
    Explanations

    electrical components

    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
    为什么
    -0.08
    通过
    -0.07
    Increase
    -0.07
    為什麼
    -0.07
     Increase
    -0.07
    增加
    -0.07
    位于
    -0.07
     dianggap
    -0.07
    包含
    -0.06
     Reuters
    -0.06
    POSITIVE LOGITS
     enthusi
    0.07
    த்தல்
    0.06
     original
    0.05
    originals
    0.05
     affluent
    0.05
     desire
    0.05
     grinders
    0.05
     primit
    0.05
     peruse
    0.05
     ister
    0.05
    Activations Density 0.030%

    No Known Activations