© 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. 129531
    Prev
    Next
    INDEX
    Explanations

    syntax, mode, ways, detailed

    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
    せずに
    -0.06
     சும
    -0.06
     muod
    -0.06
     পরিকল্পনা
    -0.06
     কতটা
    -0.06
     either
    -0.06
     Biasanya
    -0.06
     presup
    -0.06
    course
    -0.06
     خطر
    -0.06
    POSITIVE LOGITS
     amazing
    0.07
    いくつか
    0.06
     unrival
    0.06
     revolutionary
    0.06
     EU
    0.06
     admirable
    0.06
     त्याच
    0.06
     unsurpassed
    0.06
    رحب
    0.06
    EU
    0.06
    Activations Density 0.009%

    No Known Activations