© 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. 128964
    Prev
    Next
    INDEX
    Explanations

    subject to revision

    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
     Abnormal
    -0.07
     erreur
    -0.06
    错误
    -0.06
     abnormal
    -0.06
     běž
    -0.06
    Crazy
    -0.06
     अक्सर
    -0.06
     لیاقت
    -0.06
    essential
    -0.06
     Various
    -0.06
    POSITIVE LOGITS
     मुसी
    0.07
     역사
    0.06
     (?)
    0.06
    rootDir
    0.06
     акчага
    0.06
     થયો
    0.06
    튿
    0.06
    etzte
    0.06
     folks
    0.05
     sovr
    0.05
    Activations Density 0.001%

    No Known Activations