© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130835
    Prev
    Next
    INDEX
    Explanations

    now, now that, now is

    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
    İ
    -0.06
     varient
    -0.06
     Harness
    -0.06
    ドキ
    -0.06
    whom
    -0.06
    ymp
    -0.06
     நேரம்
    -0.06
     Done
    -0.06
    nih
    -0.06
    Done
    -0.06
    POSITIVE LOGITS
     теперь
    0.07
     junto
    0.07
     şimdi
    0.06
     ahora
    0.06
     జన్
    0.06
     wann
    0.06
    如今
    0.06
     علاوه
    0.06
     now
    0.06
     البته
    0.06
    Activations Density 0.038%

    No Known Activations