© 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. 128989
    Prev
    Next
    INDEX
    Explanations

    conventional or previous methods

    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
    しかも
    -0.07
     पीछ
    -0.07
    including
    -0.07
    Moreover
    -0.07
     attorneys
    -0.06
    members
    -0.06
    ători
    -0.06
     शेअर
    -0.06
    byshev
    -0.06
    以上の
    -0.06
    POSITIVE LOGITS
     overall
    0.07
     EX
    0.06
     Iglesias
    0.06
    ;
    0.05
    ถูก
    0.05
     GOT
    0.05
     topic
    0.05
     MAX
    0.05
    डली
    0.05
     Ex
    0.05
    Activations Density 0.004%

    No Known Activations