© 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. 128799
    Prev
    Next
    INDEX
    Explanations

    begin environment

    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
     조합
    -0.06
    大幅
    -0.06
     što
    -0.06
    混合
    -0.06
     μεταξύ
    -0.06
     totale
    -0.06
    Combination
    -0.05
    かな
    -0.05
     mixed
    -0.05
    መለ
    -0.05
    POSITIVE LOGITS
     безпе
    0.07
     the
    0.06
     reluctance
    0.06
     naszego
    0.06
     ORDIN
    0.06
     Goes
    0.06
    рона
    0.06
     защи
    0.06
     corresponding
    0.06
     цього
    0.05
    Activations Density 0.003%

    No Known Activations