© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129922
    Prev
    Next
    INDEX
    Explanations

    this software, file, notice, photograph

    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
     innych
    -0.08
     інших
    -0.07
    相關
    -0.07
     outras
    -0.07
     tutte
    -0.07
    七
    -0.06
     άλλ
    -0.06
     другие
    -0.06
    autres
    -0.06
     otras
    -0.06
    POSITIVE LOGITS
     Slightly
    0.06
    ?
    0.06
    至
    0.06
     entertain
    0.06
    Upgradeable
    0.05
    !?
    0.05
     至
    0.05
    ?!?
    0.05
              
    0.05
     ऐसे
    0.05
    Activations Density 0.011%

    No Known Activations