© 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. 120025
    Prev
    Next
    INDEX
    Explanations

    LICENSE, URL, copyright notices

    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
     will
    -0.08
     methods
    -0.07
     خواهد
    -0.06
     or
    -0.06
     нынеш
    -0.06
     будете
    -0.06
     began
    -0.06
     પ્રકાર
    -0.06
     comenzó
    -0.05
    ?!
    -0.05
    POSITIVE LOGITS
    ल्पना
    0.06
     incluidos
    0.06
     utilizamos
    0.06
     jedną
    0.06
    んじゃない
    0.06
    到
    0.06
     uso
    0.06
    对
    0.05
     છીએ
    0.05
     কিন্তু
    0.05
    Activations Density 0.025%

    No Known Activations