© 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. 119281
    Prev
    Next
    INDEX
    Explanations

    digitization, transcription, archives, made

    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
     only
    -0.07
    كثر
    -0.07
     лишь
    -0.07
     tylko
    -0.06
     только
    -0.06
     тільки
    -0.06
     فقط
    -0.06
     look
    -0.06
     claims
    -0.06
     अपील
    -0.06
    POSITIVE LOGITS
     असह
    0.06
     перевод
    0.06
    สนใจ
    0.06
    詳細
    0.06
     detal
    0.06
     agnostic
    0.06
     turning
    0.06
     intoler
    0.05
     courageous
    0.05
    paring
    0.05
    Activations Density 0.005%

    No Known Activations