© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118673
    Prev
    Next
    INDEX
    Explanations

    parts of words end with 'o', 'd', 'r'

    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
    에
    -0.06
    ದಯ
    -0.06
     能
    -0.06
     বৃত্তান্ত
    -0.06
    สึก
    -0.06
    第二
    -0.06
     menghad
    -0.06
     )[
    -0.06
    मति
    -0.06
     suhu
    -0.06
    POSITIVE LOGITS
     paperwork
    0.06
     altru
    0.06
     largas
    0.06
    댕
    0.06
     mammoth
    0.06
     lifeline
    0.06
    キャッシュ
    0.06
    BIG
    0.06
    ROLL
    0.06
     bool
    0.06
    Activations Density 0.009%

    No Known Activations