© 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. 130681
    Prev
    Next
    INDEX
    Explanations

    personal discovery or observation

    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
     each
    -0.08
     some
    -0.07
     one
    -0.06
     jakiś
    -0.06
    each
    -0.06
     arguably
    -0.06
     Trade
    -0.06
    เลือก
    -0.06
     evidentemente
    -0.06
     Each
    -0.06
    POSITIVE LOGITS
     později
    0.07
    ələ
    0.06
     toate
    0.06
    当我
    0.06
     schönsten
    0.06
    굵
    0.06
     ځای
    0.06
     holde
    0.06
     내가
    0.06
     handles
    0.06
    Activations Density 0.010%

    No Known Activations