© 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. 116382
    Prev
    Next
    INDEX
    Explanations

    entity name beginnings

    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
     như
    -0.07
     como
    -0.06
    比如
    -0.06
    forever
    -0.06
     معرف
    -0.06
    comme
    -0.06
    如
    -0.06
     like
    -0.06
     как
    -0.06
    に係る
    -0.06
    POSITIVE LOGITS
     साई
    0.06
     nume
    0.06
     sizes
    0.06
     Jumlah
    0.06
     její
    0.06
     approaches
    0.06
     গঠিত
    0.06
    śli
    0.06
    ELIST
    0.06
     dispoz
    0.06
    Activations Density 0.001%

    No Known Activations