© 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. 119722
    Prev
    Next
    INDEX
    Explanations

    pull, MurmurHash, Remove, Apache, Q:, Are multiple, Targeted, In vitro

    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
    🤩
    -0.06
    cccnc
    -0.06
     admi
    -0.06
     bonsai
    -0.06
     telescopic
    -0.06
     появились
    -0.06
     Chop
    -0.06
    楽天市場
    -0.06
     상세
    -0.06
     formally
    -0.05
    POSITIVE LOGITS
    过来的
    0.07
    getting
    0.07
     getting
    0.06
    卫生
    0.06
    に取り組
    0.06
     Insulin
    0.06
     insulin
    0.06
     Sicherheit
    0.06
    being
    0.06
    就像
    0.06
    Activations Density 0.001%

    No Known Activations