© 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. 120532
    Prev
    Next
    INDEX
    Explanations

    version number scheme

    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
    ളു
    -0.06
     uncommon
    -0.06
    taste
    -0.06
     constitution
    -0.06
     आपको
    -0.06
     obecnie
    -0.06
     ब्लड
    -0.05
     you
    -0.05
     त्याच्या
    -0.05
     rare
    -0.05
    POSITIVE LOGITS
     scheduled
    0.07
     damit
    0.06
     گذا
    0.06
    マネ
    0.06
    planned
    0.06
    ोली
    0.06
     Expressions
    0.06
     Appraisal
    0.06
     During
    0.06
     예정
    0.06
    Activations Density 0.007%

    No Known Activations