© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128630
    Prev
    Next
    INDEX
    Explanations

    reading and processing lines

    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
     some
    -0.07
     aspirations
    -0.06
     alcune
    -0.06
    icots
    -0.06
     بعض
    -0.06
     Event
    -0.06
     accompanying
    -0.06
    event
    -0.06
     alcuni
    -0.06
    θούν
    -0.05
    POSITIVE LOGITS
    就是
    0.07
     হইতেই
    0.07
    良かった
    0.06
     schon
    0.06
    +'.
    0.06
    ると
    0.06
     podľa
    0.06
    LetterIndex
    0.06
     istilah
    0.06
    অথ
    0.06
    Activations Density 0.001%

    No Known Activations