© 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. 119319
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
     publicaciones
    -0.06
     публикации
    -0.06
     serta
    -0.06
     earth
    -0.06
     গন্ধ
    -0.05
    earth
    -0.05
     nevoie
    -0.05
     loopholes
    -0.05
     публика
    -0.05
    dling
    -0.05
    POSITIVE LOGITS
     יש
    0.07
    Roger
    0.07
    都有
    0.07
     postoji
    0.06
     있으
    0.06
    Tiene
    0.06
     აქვს
    0.06
     theres
    0.06
     există
    0.06
     terminates
    0.06
    Activations Density 0.001%

    No Known Activations