© 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. 117166
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

    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
    扩大
    -0.06
    stanbul
    -0.06
    渺
    -0.06
    দৌ
    -0.06
    悠
    -0.06
     kial
    -0.06
     IgM
    -0.06
    Shopping
    -0.06
    与其他
    -0.06
    nsan
    -0.06
    POSITIVE LOGITS
     !!
    0.06
    !!
    0.06
     Successfully
    0.06
     вместе
    0.06
     seasons
    0.06
     guests
    0.06
     hè
    0.06
     SUCCESSFULLY
    0.05
     auch
    0.05
    cstring
    0.05
    Activations Density 0.002%

    No Known Activations