© 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. 117195
    Prev
    Next
    INDEX
    Explanations

    specific word prefixes

    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
     মিডি
    -0.06
    形式
    -0.06
     to
    -0.05
    ᴍ
    -0.05
     nations
    -0.05
     acknowledge
    -0.05
     duel
    -0.05
     opposite
    -0.05
     अनुरोध
    -0.05
     Type
    -0.05
    POSITIVE LOGITS
     cây
    0.07
    有不少
    0.07
     станет
    0.06
    俨
    0.06
    ాత్ర
    0.06
     something
    0.06
     행동
    0.06
     our
    0.06
    ACTION
    0.06
     가지고
    0.06
    Activations Density 0.002%

    No Known Activations