© 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. 119379
    Prev
    Next
    INDEX
    Explanations

    code formatting and types

    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
     también
    -0.07
     également
    -0.07
     также
    -0.07
     réalité
    -0.07
     também
    -0.07
    你也
    -0.06
     מס
    -0.06
     Также
    -0.06
     etiam
    -0.06
     also
    -0.06
    POSITIVE LOGITS
    njih
    0.06
     when
    0.06
    当我
    0.06
    Every
    0.06
     depending
    0.06
     if
    0.06
    WHEN
    0.06
    ουμε
    0.06
     используются
    0.05
    िया
    0.05
    Activations Density 0.002%

    No Known Activations