© 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. 116414
    Prev
    Next
    INDEX
    Explanations

    otherwise

    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
    !!!
    -0.07
    !!!!!
    -0.06
    !!!!!!
    -0.06
    !!!!!!!
    -0.06
    !!!!
    -0.06
     vermutlich
    -0.06
     probably
    -0.06
    !
    -0.06
     have
    -0.06
     faster
    -0.06
    POSITIVE LOGITS
    otherwise
    0.07
    дук
    0.06
     Otherwise
    0.06
     করছিলেন
    0.06
     ප්‍රති
    0.06
     वगैरह
    0.06
     काटकर
    0.06
     иначе
    0.06
    Otherwise
    0.06
    endio
    0.06
    Activations Density 0.001%

    No Known Activations