© 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. 120199
    Prev
    Next
    INDEX
    Explanations

    electrons and holes

    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
     restricts
    -0.07
     prevents
    -0.07
    ające
    -0.06
     impide
    -0.06
     habe
    -0.06
     বিশ্রাম
    -0.06
     provides
    -0.06
     globally
    -0.06
     محدود
    -0.06
     preventing
    -0.06
    POSITIVE LOGITS
    .(\
    0.06
     такой
    0.06
     cosidd
    0.06
     of
    0.06
    .)
    0.06
     количеством
    0.05
    がい
    0.05
     cependant
    0.05
     first
    0.05
    굼
    0.05
    Activations Density 0.003%

    No Known Activations