© 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. 129632
    Prev
    Next
    INDEX
    Explanations

    Environmental factors, binding, communications

    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
    Its
    -0.07
     no
    -0.06
    খি
    -0.05
    ĕ
    -0.05
    yay
    -0.05
    yad
    -0.05
     আনন্দের
    -0.05
     означает
    -0.05
     would
    -0.05
     its
    -0.05
    POSITIVE LOGITS
     अनेक
    0.08
    ামিটার
    0.07
     چندین
    0.07
     actions
    0.07
     cientos
    0.06
     ninguém
    0.06
    Facebook
    0.06
     enormes
    0.06
     effort
    0.06
     একাধিক
    0.06
    Activations Density 0.003%

    No Known Activations