© 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. 116259
    Prev
    Next
    INDEX
    Explanations

    Day or Night Shifts

    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
    就知道
    -0.08
     соответствующие
    -0.06
     masch
    -0.06
     सन्
    -0.06
    就可以了
    -0.06
    iveau
    -0.06
    âncias
    -0.06
    лева
    -0.06
     сай
    -0.05
     treatments
    -0.05
    POSITIVE LOGITS
     समेत
    0.07
     désormais
    0.07
     artık
    0.06
     increasingly
    0.06
     Cá
    0.06
    эф
    0.06
     adesso
    0.06
    andid
    0.06
    koliko
    0.06
     predominantly
    0.06
    Activations Density 0.066%

    No Known Activations