© 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. 118000
    Prev
    Next
    INDEX
    Explanations

    foreign language comments

    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
     उनको
    -0.06
    প্যাথ
    -0.06
    (?)
    -0.06
    henyl
    -0.06
     sitios
    -0.06
    னில்
    -0.06
     जिनको
    -0.06
     kalau
    -0.06
     placed
    -0.06
     Sem
    -0.06
    POSITIVE LOGITS
     from
    0.07
    十几
    0.07
     продолжает
    0.06
     continuer
    0.06
    entries
    0.06
     ülke
    0.06
    iesis
    0.06
    อะคาเดมี
    0.06
     randomness
    0.06
     teen
    0.06
    Activations Density 0.014%

    No Known Activations