© 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. 129135
    Prev
    Next
    INDEX
    Explanations

    numbers and alphanumeric sequences

    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
     twenty
    -0.07
    twenty
    -0.06
    ទៀត
    -0.06
     двадцать
    -0.06
    னையும்
    -0.06
    !
    -0.06
    你
    -0.06
    、
    -0.06
     które
    -0.05
     ваше
    -0.05
    POSITIVE LOGITS
    そのため
    0.07
    ოტ
    0.06
     első
    0.06
     Darüber
    0.06
     Logitech
    0.06
    беріга
    0.06
    Bsky
    0.06
     primeiro
    0.06
     đa
    0.06
     क्रमा
    0.06
    Activations Density 0.011%

    No Known Activations