© 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. 130685
    Prev
    Next
    INDEX
    Explanations

    Starts instructional 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
    ؛
    -0.06
     for
    -0.06
     ABA
    -0.06
     as
    -0.06
    Altern
    -0.05
     এরকম
    -0.05
     the
    -0.05
    こういう
    -0.05
     this
    -0.05
    在這
    -0.05
    POSITIVE LOGITS
     awesome
    0.07
    awesome
    0.06
     odors
    0.06
     incluidos
    0.06
    包括
    0.06
     दूंगा
    0.06
    、【
    0.06
    faat
    0.06
    zilla
    0.06
     honored
    0.06
    Activations Density 0.066%

    No Known Activations