© 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. 128324
    Prev
    Next
    INDEX
    Explanations

    red carpet, after party, leaving a

    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
     detract
    -0.06
    内の
    -0.06
     genuinely
    -0.06
     ശബ്
    -0.06
     mídia
    -0.06
     formerly
    -0.06
     defunct
    -0.06
     alternately
    -0.06
     Formerly
    -0.06
     occasionally
    -0.06
    POSITIVE LOGITS
     wonderland
    0.06
     namelijk
    0.06
    뒤
    0.06
     همین
    0.06
    드
    0.06
     mondo
    0.06
    respons
    0.06
    ିକ
    0.06
    roots
    0.06
     কেমন
    0.06
    Activations Density 0.026%

    No Known Activations