© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128256
    Prev
    Next
    INDEX
    Explanations

    you have / you must

    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
     später
    -0.06
     you
    -0.06
     they
    -0.06
     gravy
    -0.06
    they
    -0.06
    有时候
    -0.06
    reported
    -0.06
    Your
    -0.05
    你说
    -0.05
    あなたは
    -0.05
    POSITIVE LOGITS
     are
    0.07
     तो
    0.07
     के
    0.07
     అనేది
    0.06
     하는
    0.06
     represents
    0.06
     is
    0.06
     will
    0.06
     olacaktır
    0.06
     PROJECTS
    0.06
    Activations Density 0.007%

    No Known Activations