© 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. 129217
    Prev
    Next
    INDEX
    Explanations

    individual items

    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
    Paul
    -0.06
     ጠ
    -0.06
     অধিকাংশই
    -0.06
    님의
    -0.05
     Paul
    -0.05
     torch
    -0.05
    ortex
    -0.05
     ungroup
    -0.05
    ogluc
    -0.05
    廃棄
    -0.05
    POSITIVE LOGITS
     вообще
    0.07
     There
    0.07
    我们
    0.07
    있다
    0.06
     অবশেষে
    0.06
    它
    0.06
     언제
    0.06
     बेहतर
    0.06
     années
    0.06
     контроли
    0.06
    Activations Density 0.007%

    No Known Activations