© 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. 120658
    Prev
    Next
    INDEX
    Explanations

    other languages or other

    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
     our
    -0.08
    我
    -0.06
    疑惑
    -0.06
     my
    -0.06
     us
    -0.06
     conno
    -0.06
     nuestra
    -0.06
    आईपी
    -0.06
    FTR
    -0.06
     দুর্দ
    -0.05
    POSITIVE LOGITS
     другие
    0.09
     другой
    0.08
    同じ
    0.08
     másik
    0.08
     다른
    0.08
     другого
    0.07
     other
    0.07
     دیگر
    0.07
     andere
    0.07
    他の
    0.07
    Activations Density 0.037%

    No Known Activations