© 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. 119823
    Prev
    Next
    INDEX
    Explanations

    application or Countdown

    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
     so
    -0.06
     sortie
    -0.06
     khiến
    -0.06
     hunch
    -0.06
    ственной
    -0.06
     sareng
    -0.06
    िवी
    -0.06
     होतं
    -0.06
     ಮಕ್ಕ
    -0.06
     haline
    -0.06
    POSITIVE LOGITS
     ключ
    0.06
     cumbersome
    0.06
    traded
    0.06
     utiliza
    0.05
     exchanged
    0.05
     glassware
    0.05
    键
    0.05
    Provided
    0.05
     ఇతర
    0.05
     utilizan
    0.05
    Activations Density 0.001%

    No Known Activations