© 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. 129585
    Prev
    Next
    INDEX
    Explanations

    keratinocytes

    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
    organic
    -0.07
     imprecise
    -0.07
     posiad
    -0.06
     podendo
    -0.06
     manipulations
    -0.06
    แก้ไข
    -0.06
     manipulating
    -0.06
    如果在
    -0.06
     opera
    -0.06
    上が
    -0.06
    POSITIVE LOGITS
    appartement
    0.06
     robustness
    0.06
     مجموعة
    0.05
     Untersuchung
    0.05
     супру
    0.05
     Какие
    0.05
    introduction
    0.05
    usto
    0.05
    什麼
    0.05
     অভ্যন্তরীণ
    0.05
    Activations Density 0.005%

    No Known Activations