© 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. 128828
    Prev
    Next
    INDEX
    Explanations

    FEV measurements and Q&A markers

    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
     expense
    -0.06
     overpriced
    -0.06
     pricey
    -0.06
    infile
    -0.06
     thoughtfully
    -0.06
     numerically
    -0.06
    point
    -0.06
     frivol
    -0.06
    minimal
    -0.05
    kring
    -0.05
    POSITIVE LOGITS
    कई
    0.07
     ഇന്ത്യൻ
    0.06
     många
    0.06
    AllResult
    0.06
     birçok
    0.06
     ребенок
    0.06
    様々な
    0.06
     वैज्ञानिकों
    0.06
     relaciona
    0.06
     другое
    0.06
    Activations Density 0.002%

    No Known Activations