© 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. 117864
    Prev
    Next
    INDEX
    Explanations

    start of names or phrases

    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
     provides
    -0.07
    ᱒
    -0.07
     offensively
    -0.07
     эпи
    -0.06
     provide
    -0.06
     poskyt
    -0.06
     awesome
    -0.06
    arsanız
    -0.06
     providing
    -0.06
     templo
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.07
     그의
    0.07
     likely
    0.07
    ↵
    0.06
     his
    0.06
    /////////
    0.06
    likely
    0.06
     അദ്ദേഹ
    0.06
    ↵↵↵↵
    0.06
    ↵↵↵↵↵↵
    0.06
    Activations Density 0.002%

    No Known Activations