© 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. 117540
    Prev
    Next
    INDEX
    Explanations

    implements interfaces

    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
     vividly
    -0.06
    ခဲ့
    -0.06
     stumbling
    -0.06
     tak
    -0.06
     wrest
    -0.06
     また
    -0.06
    奖励
    -0.06
    ियो
    -0.05
     dict
    -0.05
     Aś
    -0.05
    POSITIVE LOGITS
    이라면
    0.07
     about
    0.07
     obsług
    0.07
    طفال
    0.07
    closer
    0.06
    indic
    0.06
     আশেপাশে
    0.06
     Moshe
    0.06
     so
    0.06
    auga
    0.05
    Activations Density 0.001%

    No Known Activations