© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128134
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    Negative Logits
    omely
    -0.07
    -0.07
     नही
    -0.07
    ꒱
    -0.07
     أن
    -0.07
     wahrscheinlich
    -0.07
     أص
    -0.07
     пять
    -0.07
     همچنین
    -0.07
    这也
    -0.06
    POSITIVE LOGITS
    𝙷
    0.06
    性と
    0.06
    C
    0.06
    minimal
    0.06
     beautiful
    0.06
    1
    0.05
    AA
    0.05
     finished
    0.05
     wonderful
    0.05
    Every
    0.05
    Activations Density 0.013%

    No Known Activations