© 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. 119197
    Prev
    Next
    INDEX
    Explanations

    given names

    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
     বিভিন্ন
    -0.06
     अभिनय
    -0.06
     വിവിധ
    -0.06
     பகுதியில்
    -0.06
     ड
    -0.06
     verschillende
    -0.06
    ванням
    -0.05
     různých
    -0.05
    aspect
    -0.05
    autista
    -0.05
    POSITIVE LOGITS
    也被
    0.06
    也可
    0.06
     their
    0.06
    也是
    0.06
     Easily
    0.06
    ､
    0.06
     जैसा
    0.06
     thorough
    0.06
     நிதி
    0.06
    isk
    0.06
    Activations Density 0.017%

    No Known Activations