© 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. 120513
    Prev
    Next
    INDEX
    Explanations

    various language number words

    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
    6
    -0.07
    7
    -0.06
    「
    -0.06
    4
    -0.06
    5
    -0.06
    この
    -0.06
    8
    -0.06
    ("
    -0.06
    XXXX
    -0.06
     currently
    -0.06
    POSITIVE LOGITS
     चार
    0.08
     entretenimiento
    0.07
     первую
    0.07
     trois
    0.07
     மூன்று
    0.07
     মাজ
    0.07
     solche
    0.07
     vijf
    0.07
     nuova
    0.07
     salaire
    0.07
    Activations Density 0.041%

    No Known Activations