© 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. 130722
    Prev
    Next
    INDEX
    Explanations

    again

    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
     this
    -0.06
     if
    -0.06
     éstos
    -0.06
     éste
    -0.06
    この
    -0.06
     éstas
    -0.06
    hos
    -0.05
     এই
    -0.05
     তাকে
    -0.05
    ()
    -0.05
    POSITIVE LOGITS
     openly
    0.08
     infamous
    0.07
    又有
    0.07
    Again
    0.07
     비슷한
    0.07
     또
    0.07
    再度
    0.07
     kolejne
    0.06
     znovu
    0.06
     influential
    0.06
    Activations Density 0.046%

    No Known Activations