© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118162
    Prev
    Next
    INDEX
    Explanations

    URL or web link identifiers

    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
     such
    -0.07
     zároveň
    -0.06
     یعنی
    -0.06
     rua
    -0.06
     नाही
    -0.06
     এমনকি
    -0.06
     میتوان
    -0.06
     this
    -0.06
    这种
    -0.06
     aslında
    -0.06
    POSITIVE LOGITS
     for
    0.07
    を
    0.07
     và
    0.07
     и
    0.06
     και
    0.06
    ¥
    0.06
    하고
    0.06
    ackle
    0.06
    ಂದು
    0.05
     খেয়ে
    0.05
    Activations Density 0.009%

    No Known Activations