© 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. 119996
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    乃至
    -0.07
     reuse
    -0.06
     Reuse
    -0.06
     report
    -0.06
     آفس
    -0.06
     recycling
    -0.06
     ¬
    -0.05
     Nie
    -0.05
    Needed
    -0.05
     ARCH
    -0.05
    POSITIVE LOGITS
     with
    0.06
     স্থানীয়
    0.06
     acum
    0.06
     বেশ
    0.06
     educación
    0.06
     വാഹന
    0.06
     গ্রন্থের
    0.06
     لوگوں
    0.06
     defocus
    0.06
    人は
    0.06
    Activations Density 0.001%

    No Known Activations