© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130009
    Prev
    Next
    INDEX
    Explanations

    parenthetical birth or alternative 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
     gemäß
    -0.06
     యూ
    -0.06
     innerhalb
    -0.06
     truce
    -0.06
    its
    -0.06
     its
    -0.06
     indicating
    -0.06
     표시
    -0.06
     exaggerated
    -0.06
    ेत
    -0.06
    POSITIVE LOGITS
    從
    0.08
    从
    0.06
     자신이
    0.06
     シュ
    0.06
     যাবতীয়
    0.06
     conseguiu
    0.06
    去世
    0.06
     हफ्ते
    0.06
     PAK
    0.05
    NameTo
    0.05
    Activations Density 0.016%

    No Known Activations