© 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. 128400
    Prev
    Next
    INDEX
    Explanations

    indirectly followed by a consequence or method

    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
    应该
    -0.06
    шаем
    -0.06
    बाजी
    -0.05
    _{(
    -0.05
     sekolah
    -0.05
     Quiet
    -0.05
    が必要です
    -0.05
     zusätz
    -0.05
     extraneous
    -0.05
     ऊ
    -0.05
    POSITIVE LOGITS
     мечта
    0.07
     Только
    0.07
     indirectly
    0.06
     ríos
    0.06
     ١
    0.06
    addresses
    0.06
     Claro
    0.06
    ٸ
    0.06
     আগুন
    0.06
    第三方
    0.06
    Activations Density 0.003%

    No Known Activations