© 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. 119333
    Prev
    Next
    INDEX
    Explanations

    outdated information

    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
     reworking
    -0.07
     changing
    -0.06
    可知
    -0.06
     restructure
    -0.06
     will
    -0.06
     unfore
    -0.06
    可能會
    -0.06
     unforeseen
    -0.06
     verrà
    -0.06
    に変更
    -0.06
    POSITIVE LOGITS
    ເຮັດ
    0.06
     kontroll
    0.06
     meer
    0.06
    itie
    0.06
    obtained
    0.05
     familiar
    0.05
     Lew
    0.05
    Fighting
    0.05
     controll
    0.05
    Lew
    0.05
    Activations Density 0.002%

    No Known Activations