© 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. 119451
    Prev
    Next
    INDEX
    Explanations

    ideas, ages, times, new, before, obvious

    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
    jegyz
    -0.06
     bırak
    -0.05
     as
    -0.05
     பரிந்து
    -0.05
     fluorine
    -0.05
    oisin
    -0.05
     short
    -0.05
    less
    -0.05
     circumstantial
    -0.05
    pośred
    -0.05
    POSITIVE LOGITS
    計算
    0.08
     최대
    0.07
    最大
    0.07
     способны
    0.07
     कितने
    0.07
    Hero
    0.06
     способен
    0.06
    计算
    0.06
     hesap
    0.06
     mampu
    0.06
    Activations Density 0.033%

    No Known Activations