© 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. 117002
    Prev
    Next
    INDEX
    Explanations

    special characters followed by `the`

    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
     tantamount
    -0.06
     incentives
    -0.06
     totality
    -0.06
     moreover
    -0.06
     transcendence
    -0.06
     tasteful
    -0.05
    !!!!!!
    -0.05
    !!!!!!!
    -0.05
     mile
    -0.05
    POSITIVE LOGITS
     richiede
    0.07
     Boyd
    0.07
     choices
    0.06
    ुकी
    0.06
     Inglis
    0.06
    upstream
    0.06
     시간이
    0.06
     불안
    0.06
    排水
    0.06
     Opinions
    0.06
    Activations Density 0.016%

    No Known Activations