© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117497
    Prev
    Next
    INDEX
    Explanations

    known as

    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
    对他
    -0.06
    nye
    -0.06
     дета
    -0.06
     দখল
    -0.06
    appoint
    -0.06
     yet
    -0.06
     Pint
    -0.06
     লিপিবদ্ধ
    -0.06
     النوع
    -0.06
    रिज
    -0.05
    POSITIVE LOGITS
     supplemented
    0.07
     combined
    0.06
    をつけて
    0.06
     قومی
    0.06
     quase
    0.06
    combined
    0.06
     converted
    0.06
     έχουν
    0.06
     Combined
    0.06
     rotated
    0.06
    Activations Density 0.007%

    No Known Activations