© 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. 117375
    Prev
    Next
    INDEX
    Explanations

    Prefixes followed by specific 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
     বয়স্ক
    -0.06
     поскольку
    -0.06
     전부
    -0.05
     aesthetics
    -0.05
     aren
    -0.05
     Bots
    -0.05
    ",
    -0.05
    넌
    -0.05
     दिल्या
    -0.05
     desto
    -0.05
    POSITIVE LOGITS
     on
    0.08
     சமீப
    0.06
     careless
    0.06
     fakat
    0.06
    鏂
    0.06
     Keychain
    0.06
     guer
    0.06
     სტ
    0.06
    實驗
    0.06
    সভ
    0.06
    Activations Density 0.001%

    No Known Activations