© 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. 116657
    Prev
    Next
    INDEX
    Explanations

    photorefractive keratectomy

    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
    Ar
    -0.06
     Rats
    -0.06
    Ab
    -0.06
    plastic
    -0.06
    Se
    -0.06
    នៅលើ
    -0.06
     Acute
    -0.06
     আশ্রয়
    -0.06
     obligación
    -0.05
    ύ
    -0.05
    POSITIVE LOGITS
     등이
    0.07
     आर्थिक
    0.07
     Jens
    0.06
    も
    0.06
     refor
    0.06
     timeout
    0.06
     baan
    0.06
    attered
    0.06
    復活
    0.06
     njima
    0.06
    Activations Density 0.016%

    No Known Activations